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

    Neuronpedia

    INDEX
    Explanations

    Auto, nickname, abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     unidos
    0.43
    लीवुड
    0.41
    通
    0.40
     formats
    0.39
     Assert
    0.38
    Permalink
    0.38
    קב
    0.37
    Formats
    0.37
     berupa
    0.37
     Assertion
    0.36
    POSITIVE LOGITS
     மாறி
    0.43
     satir
    0.41
    窅
    0.40
     ожида
    0.38
    idem
    0.38
     croy
    0.37
    贫
    0.37
    dumb
    0.37
     dumb
    0.36
    leti
    0.35
    Act Density 0.000%

    No Known Activations