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

    Neuronpedia

    INDEX
    Explanations

    SPECIAL

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     worried
    -0.07
    _mac
    -0.07
     coins
    -0.07
    昃
    -0.07
    bcd
    -0.07
    conditions
    -0.07
    人死亡
    -0.06
    丙
    -0.06
    xEC
    -0.06
    chio
    -0.06
    POSITIVE LOGITS
     Residence
    0.07
    _ACCESS
    0.07
     Ranked
    0.07
    Ranges
    0.07
    _Release
    0.07
    _rotate
    0.07
    _ING
    0.07
    帰
    0.07
    Knowledge
    0.07
     Knights
    0.07
    Act Density 0.001%

    No Known Activations