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

    Neuronpedia

    INDEX
    Explanations

    academic papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [vertex
    -0.07
     Parad
    -0.07
    .board
    -0.07
    ेट
    -0.06
     keyword
    -0.06
    RITE
    -0.06
     افز
    -0.06
     aus
    -0.06
     dissertation
    -0.06
    pot
    -0.06
    POSITIVE LOGITS
     böylece
    0.07
    úsqueda
    0.06
     小
    0.06
    ètre
    0.06
     Signed
    0.06
    _signed
    0.06
     metallic
    0.06
     žal
    0.06
    _cpu
    0.06
    (song
    0.06
    Act Density 0.030%

    No Known Activations