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

    Neuronpedia

    INDEX
    Explanations

    headlines or baby digital vitamins

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     දී
    0.47
     reconsideration
    0.46
     دیے
    0.45
    .].
    0.44
     धरोहर
    0.41
     prudence
    0.40
    Francis
    0.40
     Bellev
    0.40
    ByID
    0.40
    CompliancePolicy
    0.40
    POSITIVE LOGITS
     titulares
    0.47
    或者
    0.46
    baby
    0.45
     digitalen
    0.44
     vitaminas
    0.44
     หรือ
    0.43
    ក
    0.43
     baby
    0.43
     daughters
    0.43
     atau
    0.42
    Act Density 0.006%

    No Known Activations