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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    actors
    -0.07
     grd
    -0.06
    bursement
    -0.06
     ample
    -0.06
    ifty
    -0.06
    ilight
    -0.06
     अ
    -0.06
    actual
    -0.06
     木
    -0.06
     neuen
    -0.06
    POSITIVE LOGITS
    ={(
    0.06
     {:.
    0.06
    Installing
    0.06
    вропей
    0.06
     lifespan
    0.06
     CSR
    0.06
    婆
    0.06
    .nome
    0.06
     رسول
    0.06
    _MAKE
    0.06
    Act Density 0.000%

    No Known Activations