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

    Neuronpedia

    INDEX
    Explanations

    words starting with Al

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ห
    0.41
    யூ
    0.40
    eud
    0.39
    レディース
    0.38
    }}^
    0.38
    こんな
    0.37
     '-':
    0.37
    ৯০
    0.37
    इड
    0.36
    }\,
    0.36
    POSITIVE LOGITS
     Al
    0.78
     AL
    0.78
    Al
    0.70
     al
    0.65
    querque
    0.60
     알
    0.60
     アル
    0.57
     Аль
    0.57
     Alka
    0.54
     Capone
    0.54
    Act Density 0.047%

    No Known Activations