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

    Neuronpedia

    INDEX
    Explanations

    arrange items and risk assessment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    лектро
    0.42
    Méd
    0.39
    ंपूर्
    0.38
    Mods
    0.37
    stil
    0.36
    𒊑
    0.36
    演员
    0.35
    irà
    0.35
    isin
    0.35
    ]}{
    0.34
    POSITIVE LOGITS
    健
    0.40
     balik
    0.39
     terminus
    0.38
     Prisons
    0.38
     nuestro
    0.38
    ifier
    0.37
     menurunkan
    0.37
    榴
    0.37
     Nusantara
    0.37
     واحدة
    0.36
    Act Density 0.002%

    No Known Activations