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

    Neuronpedia

    INDEX
    Explanations

    say "use" or "browse"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (b
    -0.07
    Located
    -0.06
    =E
    -0.06
    Con
    -0.06
     Higher
    -0.06
    (k
    -0.06
     Is
    -0.06
    _xt
    -0.06
    .—
    -0.06
    .Vert
    -0.06
    POSITIVE LOGITS
    شة
    0.08
    يكا
    0.07
    �
    0.06
    >\<^
    0.06
     Goals
    0.06
     支
    0.06
    ичної
    0.06
    .solve
    0.06
     Pazar
    0.06
     zby
    0.06
    Act Density 0.002%

    No Known Activations