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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    algorithm
    -0.07
    Appro
    -0.07
    Purpose
    -0.07
     GEO
    -0.06
     hi
    -0.06
    ーロ
    -0.06
    Wrapped
    -0.06
    exterity
    -0.06
     zar
    -0.06
    ValuePair
    -0.06
    POSITIVE LOGITS
    --
↵
    0.07
    Neutral
    0.07
    .Simple
    0.06
    ンデ
    0.06
    าส
    0.06
     Fus
    0.06
    .fontSize
    0.06
     меш
    0.06
    سين
    0.06
    __':↵
    0.06
    Act Density 0.004%

    No Known Activations