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

    Neuronpedia

    INDEX
    Explanations

    Enron emails

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _DOMAIN
    -0.07
    촌
    -0.07
    기가
    -0.07
     Cups
    -0.07
    gorithm
    -0.07
    μου
    -0.07
    전
    -0.06
    _FIELDS
    -0.06
    utschen
    -0.06
     Sphere
    -0.06
    POSITIVE LOGITS
    ีป
    0.06
    (Size
    0.06
    oystick
    0.06
     compliant
    0.06
     strt
    0.06
     hes
    0.06
    (strings
    0.05
     focusing
    0.05
    .endsWith
    0.05
    -den
    0.05
    Act Density 0.026%

    No Known Activations