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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     restored
    -0.07
    ivery
    -0.07
    MODE
    -0.06
    po
    -0.06
    _prices
    -0.06
    METHOD
    -0.06
     votre
    -0.06
    _LINES
    -0.06
     fastest
    -0.06
    彼
    -0.06
    POSITIVE LOGITS
     emot
    0.07
     incontr
    0.06
     Tip
    0.06
     Gaza
    0.06
     entra
    0.06
     hend
    0.06
     Beats
    0.06
    cast
    0.06
     BAL
    0.06
     cos
    0.05
    Act Density 0.013%

    No Known Activations