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

    Neuronpedia

    INDEX
    Explanations

    Describing actions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    凭什么
    -0.07
    ọc
    -0.07
     detalle
    -0.07
    [msg
    -0.07
    eña
    -0.07
    _DEL
    -0.07
    🛁
    -0.06
     Każdy
    -0.06
     très
    -0.06
    🍈
    -0.06
    POSITIVE LOGITS
     Outcome
    0.08
    methods
    0.07
    켰
    0.07
     Amar
    0.07
     recon
    0.06
    -around
    0.06
     boto
    0.06
    Records
    0.06
     Punk
    0.06
     Cabinet
    0.06
    Act Density 0.096%

    No Known Activations