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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    וול
    -0.08
     REFERENCES
    -0.07
    grese
    -0.07
    .AnchorStyles
    -0.07
    וכל
    -0.07
    "path
    -0.07
    これが
    -0.07
    =json
    -0.07
    戋
    -0.06
    #pragma
    -0.06
    POSITIVE LOGITS
    isy
    0.08
     ongoing
    0.07
     backstory
    0.07
    ilia
    0.07
    sdale
    0.07
     Violence
    0.07
     Hawaii
    0.07
    Emily
    0.07
    asiswa
    0.06
    户口
    0.06
    Act Density 0.000%

    No Known Activations