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

    Neuronpedia

    INDEX
    Explanations

    &

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /template
    -0.06
    iqueta
    -0.06
    (square
    -0.06
     polit
    -0.06
    )-
    -0.06
    sert
    -0.06
    Layout
    -0.06
    \Validator
    -0.06
    queries
    -0.06
     BaseEntity
    -0.06
    POSITIVE LOGITS
    огда
    0.07
     RE
    0.07
    由于
    0.06
    rib
    0.06
     signaling
    0.06
    因为
    0.06
    mong
    0.06
    ORK
    0.06
    箱
    0.06
     disrupted
    0.06
    Act Density 0.004%

    No Known Activations