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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Smoking
    -0.08
    脱发
    -0.08
     circle
    -0.07
    /train
    -0.07
     excursion
    -0.07
    _PTR
    -0.07
     prive
    -0.07
     Train
    -0.07
     curved
    -0.07
     yeti
    -0.07
    POSITIVE LOGITS
     appreciate
    0.08
    _pars
    0.07
    对付
    0.07
     części
    0.07
    𝕤
    0.07
     practices
    0.07
     recognizing
    0.06
     recognizes
    0.06
     hợp
    0.06
    izador
    0.06
    Act Density 0.009%

    No Known Activations