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

    Neuronpedia

    INDEX
    Explanations

    staining

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cage
    -0.07
    precation
    -0.07
    II
    -0.06
    _rom
    -0.06
    -sama
    -0.06
     py
    -0.06
    listening
    -0.06
     delim
    -0.06
    ají
    -0.06
    ゝ
    -0.06
    POSITIVE LOGITS
     handwritten
    0.06
    exception
    0.06
    _INITIALIZER
    0.06
    \uC
    0.06
    ');"
    0.06
    (confirm
    0.06
    BJ
    0.06
     Appropri
    0.06
     Discipline
    0.05
    ления
    0.05
    Act Density 0.347%

    No Known Activations