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

    Neuronpedia

    INDEX
    Explanations

    toxin

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SetUp
    -0.07
    Italic
    -0.07
    gether
    -0.07
    Queue
    -0.07
    eref
    -0.07
    PED
    -0.07
     pstmt
    -0.06
    -0.06
    .bootstrapcdn
    -0.06
     unary
    -0.06
    POSITIVE LOGITS
     toxin
    0.08
    technology
    0.07
    ONUS
    0.06
    Daniel
    0.06
     бли
    0.06
    ีช
    0.06
    Way
    0.06
     Ton
    0.06
    權
    0.06
     gần
    0.06
    Act Density 0.004%

    No Known Activations