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

    Neuronpedia

    INDEX
    Explanations

    news events

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    据
    -0.07
    办
    -0.06
     últ
    -0.06
     canal
    -0.06
    脑
    -0.06
    Geometry
    -0.06
     Canal
    -0.06
     agora
    -0.06
     
    -0.06
     conting
    -0.06
    POSITIVE LOGITS
    laşma
    0.07
    kept
    0.07
    (Sender
    0.07
    _buf
    0.07
     TMP
    0.06
     IReadOnly
    0.06
    ุค
    0.06
    tees
    0.06
     **************************************************************************
    0.06
    ToOne
    0.06
    Act Density 0.084%

    No Known Activations