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

    Neuronpedia

    INDEX
    Explanations

    investment positions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     MsgBox
    -0.07
     weit
    -0.07
     ^(
    -0.07
    ,-
    -0.06
    Profit
    -0.06
    .Raycast
    -0.06
    _LS
    -0.06
     Sponge
    -0.06
     собі
    -0.06
    ================================================
    -0.06
    POSITIVE LOGITS
    711
    0.07
     Motor
    0.06
     Killing
    0.06
    282
    0.06
     Philip
    0.06
     insets
    0.06
     gấp
    0.06
     paso
    0.06
    戲
    0.06
    ۲۰۲
    0.06
    Act Density 0.005%

    No Known Activations