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

    Neuronpedia

    INDEX
    Explanations

    maybe

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     league
    -0.07
    <boolean
    -0.06
    rak
    -0.06
    reamble
    -0.06
    �
    -0.06
    시는
    -0.06
    .has
    -0.06
    irector
    -0.06
     Outs
    -0.06
    รายการ
    -0.06
    POSITIVE LOGITS
    ??
    0.07
    IBC
    0.06
    _render
    0.06
    คโนโลย
    0.06
    ,"%
    0.06
     チ
    0.06
    ocab
    0.06
    abcdefghijkl
    0.06
     wohl
    0.06
    ализации
    0.06
    Act Density 0.000%

    No Known Activations