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

    Neuronpedia

    INDEX
    Explanations

    neurological studies

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Oktober
    -0.06
    From
    -0.06
     Cornell
    -0.06
    Emitter
    -0.06
    Se
    -0.06
    ues
    -0.06
     theater
    -0.06
    Rocket
    -0.06
     TIME
    -0.06
    eft
    -0.06
    POSITIVE LOGITS
    (bp
    0.07
    ATEGY
    0.07
    (valid
    0.07
     insan
    0.07
    @register
    0.07
    _hresult
    0.07
    ，而且
    0.06
    .prot
    0.06
     사실
    0.06
    wins
    0.06
    Act Density 0.013%

    No Known Activations