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

    Neuronpedia

    INDEX
    Explanations

    {

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ansion
    -0.07
     hateful
    -0.06
    とう
    -0.06
    FI
    -0.06
     zap
    -0.06
    &quot
    -0.06
    _ATTACHMENT
    -0.06
     Lakers
    -0.06
    Accessor
    -0.06
    _ELEMENT
    -0.06
    POSITIVE LOGITS
    �
    0.08
     mourn
    0.07
     kullan
    0.06
     Ask
    0.06
    済
    0.06
    leshoot
    0.06
    Depart
    0.06
    .Annotations
    0.06
    Swift
    0.06
     TreeMap
    0.06
    Act Density 0.001%

    No Known Activations