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

    Neuronpedia

    INDEX
    Explanations

    using *apppast habitforeign birthmodel parameterscarried down

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    پيديا
    0.57
    }]$,
    0.50
     فوټبال
    0.49
    통산
    0.49
     باسکٹ
    0.49
     bonito
    0.48
     vlastní
    0.48
     fruto
    0.48
    চৈত
    0.47
    "].
    0.47
    POSITIVE LOGITS
    ad
    0.49
    od
    0.47
    w
    0.46
    as
    0.45
    eval
    0.45
    m
    0.44
     맞
    0.43
    using
    0.42
    μα
    0.42
     Alter
    0.41
    Act Density 0.000%

    No Known Activations