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

    Neuronpedia

    INDEX
    Explanations

    code and configurations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Abort
    -0.07
    qc
    -0.07
    _choice
    -0.07
     Battery
    -0.07
    .redis
    -0.06
     fabrics
    -0.06
     witches
    -0.06
     executed
    -0.06
    设计
    -0.06
     Stein
    -0.06
    POSITIVE LOGITS
     gdy
    0.06
    .from
    0.06
     grip
    0.06
     casa
    0.06
     Libyan
    0.06
     Essential
    0.06
     him
    0.06
     clr
    0.06
    ková
    0.06
    si
    0.06
    Act Density 0.001%

    No Known Activations