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

    Neuronpedia

    INDEX
    Explanations

    something or everything

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     डिवाइड
    0.44
     глуби
    0.43
    Ano
    0.41
    c
    0.41
     डूब
    0.41
    也
    0.41
    TYPE
    0.41
     col
    0.40
     बाहर
    0.40
     indi
    0.40
    POSITIVE LOGITS
    ី
    0.46
     nanom
    0.45
     AIP
    0.45
     onsite
    0.44
    跶
    0.44
    齙
    0.43
     callbacks
    0.43
     accruing
    0.43
    𝑦
    0.43
    رو
    0.42
    Act Density 0.000%

    No Known Activations