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

    Neuronpedia

    INDEX
    Explanations

    Text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     INTERRUPTION
    -0.07
     сю
    -0.06
    .TIME
    -0.06
     stakes
    -0.06
    -Sep
    -0.06
    livě
    -0.06
    etě
    -0.06
    qrt
    -0.06
    �
    -0.06
    edian
    -0.06
    POSITIVE LOGITS
     obliged
    0.07
     VIN
    0.07
    側
    0.06
     ellipse
    0.06
     bless
    0.06
    _FRONT
    0.06
    _n
    0.06
     Cin
    0.06
    一般
    0.06
    QS
    0.06
    Act Density 0.001%

    No Known Activations