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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     appliance
    -0.08
    对该
    -0.07
    习近平总
    -0.07
     Certain
    -0.07
     assessments
    -0.07
     Росс
    -0.07
    jumlah
    -0.07
    _login
    -0.07
    הר
    -0.06
    ilio
    -0.06
    POSITIVE LOGITS
     차
    0.09
    传递
    0.08
     לבצע
    0.06
     좀
    0.06
    _%
    0.06
    crafted
    0.06
    花纹
    0.06
    渗
    0.06
    _emb
    0.06
    _Syntax
    0.06
    Act Density 0.015%

    No Known Activations