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

    Neuronpedia

    INDEX
    Explanations

    Numbers and records

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ですか
    -0.07
     to
    -0.07
    oters
    -0.07
     afternoon
    -0.07
     Compatibility
    -0.07
    ственных
    -0.07
     landscape
    -0.06
    Both
    -0.06
     Seeking
    -0.06
     astr
    -0.06
    POSITIVE LOGITS
     ".$_
    0.07
    0.06
     заболеваний
    0.06
    "/><
    0.06
     ['.
    0.06
     Valk
    0.06
     NXT
    0.06
     ",");↵
    0.06
     кур
    0.06
    CppMethodIntialized
    0.06
    Act Density 0.112%

    No Known Activations