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

    Neuronpedia

    INDEX
    Explanations

    ish

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    лен
    -0.07
     empir
    -0.06
     shattered
    -0.06
     Gate
    -0.06
    253
    -0.06
     muchas
    -0.06
    265
    -0.06
    ونة
    -0.06
    eam
    -0.06
    ление
    -0.06
    POSITIVE LOGITS
    CKER
    0.07
    _IN
    0.07
     disrespect
    0.07
     Кри
    0.06
    igail
    0.06
     засід
    0.06
    □□
    0.06
     indict
    0.06
    Rep
    0.06
    _run
    0.06
    Act Density 0.002%

    No Known Activations