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

    Neuronpedia

    INDEX
    Explanations

    specific examples and outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Here
    0.48
     Knock
    0.47
     Nic
    0.46
     Ramp
    0.46
    娍
    0.46
     Cast
    0.46
    снов
    0.46
     Oxidation
    0.45
     Hall
    0.45
    ואר
    0.45
    POSITIVE LOGITS
     shortcomings
    0.51
    targets
    0.50
    targeting
    0.50
    type
    0.50
    against
    0.49
     ambiguities
    0.48
    oconvex
    0.48
     contemplating
    0.48
     dificultades
    0.48
    yses
    0.48
    Act Density 0.001%

    No Known Activations