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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Stateless
    -0.08
     supplements
    -0.08
    @api
    -0.07
    氮
    -0.07
    ActionPerformed
    -0.07
     titanium
    -0.07
    缝
    -0.07
    Normalize
    -0.07
     Alic
    -0.07
     tam
    -0.06
    POSITIVE LOGITS
     נה
    0.09
    unden
    0.08
    众所
    0.08
    ﯙ
    0.07
    草地
    0.07
    -plan
    0.07
    可谓是
    0.07
    业界
    0.07
     hayatı
    0.06
    _OPT
    0.06
    Act Density 0.030%

    No Known Activations