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

    Neuronpedia

    INDEX
    Explanations

    part of a whole

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (ld
    -0.08
    .fs
    -0.07
    _he
    -0.07
     depths
    -0.06
     б
    -0.06
    uf
    -0.06
    flows
    -0.06
    _errors
    -0.06
     breakpoint
    -0.06
     spending
    -0.06
    POSITIVE LOGITS
    ogene
    0.07
    UIStoryboardSegue
    0.06
    .GetKey
    0.06
    .cid
    0.06
    дии
    0.06
    اق
    0.06
     составе
    0.06
    .gpu
    0.06
    urr
    0.06
    agan
    0.06
    Act Density 0.044%

    No Known Activations