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

    Neuronpedia

    INDEX
    Explanations

    parameters, definitions, or lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    the
    0.51
    AN
    0.51
    EDY
    0.51
    PROTON
    0.47
    will
    0.47
    to
    0.45
    there
    0.45
    spolit
    0.45
     baratos
    0.45
     morphologies
    0.45
    POSITIVE LOGITS
    ă
    0.58
     víctima
    0.47
     earliest
    0.46
    观念
    0.46
    づくり
    0.44
    ിയാണ്
    0.44
    вала
    0.43
    өө
    0.42
    avi
    0.42
    ulum
    0.41
    Act Density 0.000%

    No Known Activations