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

    Neuronpedia

    INDEX
    Explanations

    Personal travel anecdotes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    「あ
    -0.07
    DAT
    -0.07
     Born
    -0.07
     Phone
    -0.07
     democracy
    -0.06
    ,U
    -0.06
    ;">
    -0.06
    fried
    -0.06
     pian
    -0.06
     Wick
    -0.06
    POSITIVE LOGITS
    *dt
    0.07
     minValue
    0.06
    znám
    0.06
     Reporter
    0.06
     smoothing
    0.06
    refund
    0.06
    emsp
    0.06
     Breaking
    0.06
    $v
    0.06
    گ
    0.06
    Act Density 0.007%

    No Known Activations