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

    Neuronpedia

    INDEX
    Explanations

    Cast

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vibrations
    -0.06
     microbi
    -0.06
     SubLObject
    -0.06
    -token
    -0.06
     гре
    -0.06
     Vibr
    -0.06
     кноп
    -0.05
    _tweets
    -0.05
     крит
    -0.05
     microseconds
    -0.05
    POSITIVE LOGITS
    .GetKey
    0.07
    ltre
    0.07
    PF
    0.07
     Freddie
    0.07
    berries
    0.07
    setMessage
    0.07
     专
    0.06
    っ�
    0.06
     II
    0.06
    (answer
    0.06
    Act Density 0.001%

    No Known Activations