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

    Neuronpedia

    INDEX
    Explanations

    have/with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    xcf
    -0.06
    gons
    -0.06
    ,@
    -0.06
     dov
    -0.06
     helt
    -0.06
    carry
    -0.06
    sth
    -0.06
    increment
    -0.06
    .par
    -0.06
     Immun
    -0.06
    POSITIVE LOGITS
    众
    0.07
    ء
    0.07
    ROP
    0.07
    KL
    0.06
    .H
    0.06
    <Expression
    0.06
    ولوژی
    0.06
    Cla
    0.06
    -enabled
    0.06
    quired
    0.06
    Act Density 0.027%

    No Known Activations