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

    Neuronpedia

    INDEX
    Explanations

    public

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     encountered
    -0.08
    芑
    -0.07
     Explosion
    -0.07
    疃
    -0.07
     Pistol
    -0.07
     Propel
    -0.07
     plunder
    -0.07
    _command
    -0.07
     voks
    -0.06
    bean
    -0.06
    POSITIVE LOGITS
    方形
    0.07
     Ağ
    0.07
    .grey
    0.07
     SF
    0.07
     limit
    0.07
    geh
    0.06
     publish
    0.06
     sg
    0.06
    逻辑
    0.06
    지는
    0.06
    Act Density 0.007%

    No Known Activations