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

    Neuronpedia

    INDEX
    Explanations

    So

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _TICK
    -0.07
    Https
    -0.07
     poems
    -0.07
     últimos
    -0.07
     duke
    -0.06
     değildi
    -0.06
     Subcommittee
    -0.06
    ambio
    -0.06
     araştırma
    -0.06
    (components
    -0.06
    POSITIVE LOGITS
    所以
    0.07
     нат
    0.06
    (vertex
    0.06
    salt
    0.06
     adverse
    0.06
    ไ
    0.06
    ando
    0.06
     Hence
    0.06
     탄
    0.06
    ￣￣￣￣
    0.06
    Act Density 0.051%

    No Known Activations