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

    Neuronpedia

    INDEX
    Explanations

    physical appearance and description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ACA
    0.41
     rico
    0.41
     کردیا
    0.41
    гий
    0.40
    =?
    0.38
    بخ
    0.38
    Wil
    0.38
     бага
    0.38
     !='')
    0.37
     بخ
    0.37
    POSITIVE LOGITS
    ̫
    0.42
     దు
    0.40
    ellants
    0.38
    仆
    0.38
    fords
    0.38
     Holt
    0.37
    getChild
    0.36
    }:\
    0.35
    halation
    0.34
    ELDS
    0.34
    Act Density 0.000%

    No Known Activations