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

    Neuronpedia

    INDEX
    Explanations

    k

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    窿
    -0.08
    וצא
    -0.07
     הבאים
    -0.07
    amas
    -0.07
    魃
    -0.07
    咻
    -0.07
    alen
    -0.07
    MAS
    -0.07
    ondere
    -0.07
    まれ
    -0.06
    POSITIVE LOGITS
     organizations
    0.07
    ()][
    0.07
    _hide
    0.07
     Estate
    0.07
    垂直
    0.07
     "}\
    0.07
     WTF
    0.07
     heter
    0.07
     shifting
    0.06
     patent
    0.06
    Act Density 0.001%

    No Known Activations