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

    Neuronpedia

    INDEX
    Explanations

    highly structured programming code segments and functions

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

    required elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     embarrassment
    -0.35
     internetowa
    -0.33
     krzy
    -0.31
     picada
    -0.31
    anjang
    -0.31
     Schne
    -0.31
    上
    -0.31
     Einfach
    -0.31
    encoded
    -0.30
    大
    -0.30
    POSITIVE LOGITS
    ſelf
    0.84
     queſta
    0.83
     ligiloj
    0.79
     myſelf
    0.77
    #+#
    0.72
     pleaſure
    0.71
    ⟬
    0.70
    elemField
    0.70
    tagHelperRunner
    0.69
    PerformLayout
    0.68
    Act Density 0.001%

    No Known Activations