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

    Neuronpedia

    INDEX
    Explanations

    burst

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     innocent
    -0.06
    emaakt
    -0.06
    .Cmd
    -0.06
    adera
    -0.06
    .eval
    -0.06
    Destroyed
    -0.06
    Executive
    -0.06
    plane
    -0.06
     �
    -0.06
    GRADE
    -0.06
    POSITIVE LOGITS
     burst
    0.09
     delighted
    0.08
    0.07
    _Se
    0.07
     Burst
    0.07
    cth
    0.07
    _prot
    0.07
    ossip
    0.07
     πολύ
    0.07
     sprint
    0.07
    Act Density 0.002%

    No Known Activations