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

    Neuronpedia

    INDEX
    Explanations

    censored

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Punk
    -0.07
    SSID
    -0.06
    "But
    -0.06
    达
    -0.06
     растение
    -0.06
     Sơn
    -0.06
     qualities
    -0.06
     newspapers
    -0.06
    -find
    -0.06
    ८
    -0.06
    POSITIVE LOGITS
    grp
    0.07
     graceful
    0.07
     chod
    0.06
    ultan
    0.06
    ชม
    0.06
    dej
    0.06
     Socket
    0.06
     draft
    0.06
    ducted
    0.06
    ROL
    0.06
    Act Density 0.003%

    No Known Activations