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

    Neuronpedia

    INDEX
    Explanations

    protected/public

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    vehicle
    -0.08
    ~~~~~~~~~~~~~~~~
    -0.07
    _tracks
    -0.07
     keeps
    -0.07
     Yourself
    -0.07
     Freel
    -0.07
     And
    -0.07
    家具
    -0.07
    ῄ
    -0.07
     .↵↵↵↵
    -0.07
    POSITIVE LOGITS
     prueba
    0.08
     surre
    0.07
     Mason
    0.07
     hypo
    0.07
    anitize
    0.07
     Sage
    0.07
    Capt
    0.06
    Plot
    0.06
    ippet
    0.06
    堃
    0.06
    Act Density 0.010%

    No Known Activations