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

    Neuronpedia

    INDEX
    Explanations

    Time and dates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    riot
    -0.07
    anned
    -0.07
     cambiar
    -0.06
    late
    -0.06
     rencontrer
    -0.06
     intl
    -0.06
    롭
    -0.06
     cử
    -0.06
    normalized
    -0.06
    iate
    -0.06
    POSITIVE LOGITS
     teaches
    0.08
     indice
    0.07
     Mel
    0.07
     Tested
    0.07
     geç
    0.07
    UsageId
    0.06
     intimate
    0.06
    #----------------------------------------------------------------
    0.06
    _REGS
    0.06
     Question
    0.06
    Act Density 0.072%

    No Known Activations