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

    Neuronpedia

    INDEX
    Explanations

    Extracting information from forms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AREST
    -0.07
     KDE
    -0.07
    Speak
    -0.06
     indication
    -0.06
    ONES
    -0.06
     strongest
    -0.06
    enstein
    -0.06
    eneration
    -0.06
    EFAULT
    -0.06
    plr
    -0.06
    POSITIVE LOGITS
     Literal
    0.07
     Client
    0.07
     том
    0.06
     landfill
    0.06
    .Summary
    0.06
     beige
    0.06
    (Bytes
    0.06
    妖
    0.06
    _docs
    0.06
    Qty
    0.06
    Act Density 0.011%

    No Known Activations