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

    Neuronpedia

    INDEX
    Explanations

    Places and historical records

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    blood
    -0.07
    범
    -0.07
     schwer
    -0.06
    >"
↵
    -0.06
     жовт
    -0.06
     resting
    -0.06
    桂
    -0.06
    @↵↵
    -0.06
    :",↵
    -0.06
    нож
    -0.06
    POSITIVE LOGITS
    ูไ
    0.07
    _ARG
    0.06
    _Internal
    0.06
    StoryboardSegue
    0.06
     durch
    0.06
    FFFFFF
    0.06
     fseek
    0.06
    ertia
    0.06
    YYY
    0.06
    .StackTrace
    0.06
    Act Density 0.019%

    No Known Activations