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

    Neuronpedia

    INDEX
    Explanations

    quoted text markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Out
    0.65
     Looking
    0.64
     Refresh
    0.63
     OUT
    0.60
     decisively
    0.59
     Leadership
    0.59
     Intelligence
    0.59
     Spect
    0.59
     Beyond
    0.58
     SPECT
    0.58
    POSITIVE LOGITS
    middle
    0.70
    chens
    0.65
    ostic
    0.64
    medium
    0.63
    事に
    0.61
    igheid
    0.60
    auto
    0.60
    inherit
    0.59
    odore
    0.59
    ronym
    0.59
    Act Density 0.284%

    No Known Activations