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

    Neuronpedia

    INDEX
    Explanations

    common issue

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    widget
    0.40
    菈
    0.39
     DAS
    0.38
    yness
    0.37
     itself
    0.37
     gener
    0.37
    ifal
    0.36
    ≖
    0.36
    구
    0.36
     Park
    0.35
    POSITIVE LOGITS
     compréhension
    0.45
     muro
    0.42
    omac
    0.41
     spesso
    0.40
    Xi
    0.38
     hojas
    0.38
    ksjon
    0.38
     forstå
    0.38
     occhi
    0.38
    osomes
    0.38
    Act Density 0.005%

    No Known Activations