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

    Neuronpedia

    INDEX
    Explanations

    listing disadvantages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ूँगा
    0.37
    Ро
    0.35
    阿
    0.34
     Portal
    0.33
     મ
    0.33
    Portal
    0.32
    レスレット
    0.32
    ੱ
    0.32
     comércio
    0.31
     Ро
    0.31
    POSITIVE LOGITS
     conversely
    0.62
    Conversely
    0.53
     Conversely
    0.52
    逆に
    0.41
    uddin
    0.37
    גם
    0.37
     Cohn
    0.37
     subconscious
    0.36
    unger
    0.36
     cyn
    0.35
    Act Density 0.152%

    No Known Activations