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

    Neuronpedia

    INDEX
    Explanations

    non-English text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     बातचीत
    -0.08
     compartments
    -0.08
     Wohnung
    -0.08
     महिलाओं
    -0.08
     unhealthy
    -0.07
     entrev
    -0.07
     Gespräch
    -0.07
     habitu
    -0.07
     gesprek
    -0.07
     gesprekken
    -0.07
    POSITIVE LOGITS
    予
    0.08
     bloqueo
    0.08
     ninguno
    0.08
     বদ
    0.07
     Durante
    0.07
     Blocking
    0.07
     blocked
    0.07
     bloquear
    0.07
    vano
    0.07
    picture
    0.07
    Act Density 0.000%

    No Known Activations