Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to political power dynamics and leadership transitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    followed by verbs in the past tense

    np_acts-logits-general · gemini-2.0-flash

    predecessor or successor states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     رہ
    -0.50
    InputType
    -0.46
    ონ
    -0.46
     letz
    -0.45
    @
    -0.45
     spilled
    -0.45
    cote
    -0.44
     lccn
    -0.44
    tings
    -0.43
     melahirkan
    -0.43
    POSITIVE LOGITS
     inherits
    1.11
     inherit
    1.02
     inherited
    0.96
     inher
    0.93
    ArgsConstructor
    0.91
    AddTagHelper
    0.81
    继承
    0.79
    inherited
    0.74
     predecessor
    0.73
    herited
    0.72
    Act Density 0.553%

    No Known Activations