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

    Neuronpedia

    INDEX
    Explanations

    lists/collections

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    >";↵
    -0.08
    <{
    -0.07
    #get
    -0.07
    /base
    -0.06
    ahrungen
    -0.06
    --------------------------------------------------------------------------------
    -0.06
    hotmail
    -0.06
     Ağustos
    -0.06
    },
↵
    -0.06
    ()!=
    -0.06
    POSITIVE LOGITS
    ادا
    0.07
     προς
    0.06
     Authentication
    0.06
    .SIZE
    0.06
     Patio
    0.06
    _lazy
    0.06
     Malta
    0.06
    :error
    0.06
    orex
    0.06
     GAS
    0.06
    Act Density 0.016%

    No Known Activations