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

    Neuronpedia

    INDEX
    Explanations

    list or bullet points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    )
    1.49
    "
    1.46
    es
    1.31
    .
    1.30
    }
    1.24
    :
    1.24
    _
    1.23
    ,
    1.18
    (
    1.11
    en
    1.10
    POSITIVE LOGITS
    nın
    1.34
    と呼ばれる
    1.30
    
    1.23
    ಯಲ್ಲಿ
    1.22
    <unused2130>
    1.21
     kepentingan
    1.20
     هایی
    1.16
     отношении
    1.15
     ambito
    1.10
     financieros
    1.10
    Act Density 0.606%

    No Known Activations