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

    Neuronpedia

    INDEX
    Explanations

    complex processes and operations related to development and learning

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

    facilitating work and learning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kyse
    -0.39
    SequentialGroup
    -0.38
     berta
    -0.37
    SourceChecksum
    -0.37
    ьаж
    -0.36
     publicly
    -0.35
     Sonn
    -0.35
    ={`${
    -0.34
    findpost
    -0.34
    protetor
    -0.33
    POSITIVE LOGITS
     easier
    0.90
    easier
    0.85
     Easier
    0.80
    Easier
    0.78
     efficiency
    0.78
     process
    0.75
     difficulties
    0.71
     ease
    0.70
     effectiveness
    0.70
     erleich
    0.69
    Act Density 0.083%

    No Known Activations