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

    Neuronpedia

    INDEX
    Explanations

    Numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    alité
    -0.08
    lez
    -0.07
    淫
    -0.07
     ioctl
    -0.07
    쵤
    -0.07
    >Returns
    -0.06
    对
    -0.06
    توا
    -0.06
    ност
    -0.06
     hoodie
    -0.06
    POSITIVE LOGITS
    _Parms
    0.07
    (Symbol
    0.07
    rat
    0.07
    (pre
    0.06
     принцип
    0.06
    ']}'
    0.06
    (parsed
    0.06
    ㎏
    0.06
     convictions
    0.06
    -do
    0.06
    Act Density 0.021%

    No Known Activations