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

    Neuronpedia

    INDEX
    Explanations

    alpha

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Detect
    -0.07
     Mob
    -0.07
     Goose
    -0.07
     rencontre
    -0.06
    Fin
    -0.06
     UNKNOWN
    -0.06
     distributions
    -0.06
     clash
    -0.06
    .assertNotNull
    -0.06
    -align
    -0.06
    POSITIVE LOGITS
    話
    0.07
     actresses
    0.07
     khoản
    0.07
    imary
    0.07
    .Volume
    0.07
     Ağustos
    0.06
    (query
    0.06
     ""),↵
    0.06
    Anywhere
    0.06
     comma
    0.06
    Act Density 0.003%

    No Known Activations