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

    Neuronpedia

    INDEX
    Explanations

    Science and technology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ubl
    -0.07
    (',')↵
    -0.07
    管理员
    -0.06
    Prop
    -0.06
     motifs
    -0.06
    outline
    -0.06
     Mia
    -0.06
    .readInt
    -0.06
     suede
    -0.06
     defaultProps
    -0.06
    POSITIVE LOGITS
    -L
    0.07
    ного
    0.07
    ислов
    0.06
    phasis
    0.06
    Lifecycle
    0.06
     Remain
    0.06
    loha
    0.06
     tattoo
    0.06
    73
    0.06
    Axis
    0.06
    Act Density 0.252%

    No Known Activations