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

    Neuronpedia

    INDEX
    Explanations

    memory

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bothered
    -0.07
    ubber
    -0.06
     MED
    -0.06
    Webpack
    -0.06
    iffs
    -0.06
    saida
    -0.06
    services
    -0.06
    Allow
    -0.06
    vs
    -0.06
    バス
    -0.06
    POSITIVE LOGITS
     k
    0.07
    ây
    0.06
     forKey
    0.06
     A
    0.06
    -focus
    0.06
     C
    0.06
     naive
    0.06
    .JsonProperty
    0.06
    ocab
    0.06
     Etsy
    0.06
    Act Density 0.003%

    No Known Activations