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

    Neuronpedia

    INDEX
    Explanations

    fold

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     interess
    -0.07
     Rosen
    -0.07
    ,N
    -0.07
     recursos
    -0.07
    .Some
    -0.07
     aquatic
    -0.06
    economic
    -0.06
    Auf
    -0.06
     Sach
    -0.06
    achsen
    -0.06
    POSITIVE LOGITS
     ✓
    0.07
    .ContextCompat
    0.07
    .HtmlControls
    0.07
    有关规定
    0.07
    心想
    0.07
     multiplied
    0.07
     jedną
    0.07
    _px
    0.06
     دبي
    0.06
    ()?.
    0.06
    Act Density 0.003%

    No Known Activations