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

    Neuronpedia

    INDEX
    Explanations

    without or via

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     دیا۔
    0.43
     დღ
    0.42
     carboxylic
    0.41
    owa
    0.41
    akal
    0.41
     ۲۰
    0.40
     ceva
    0.40
     benz
    0.40
     logarithms
    0.39
     हमको
    0.38
    POSITIVE LOGITS
    Identifying
    0.46
    Joseph
    0.44
    ंना
    0.43
    Without
    0.42
    Gal
    0.42
    通过
    0.42
    Tracing
    0.42
    ARD
    0.42
     बिना
    0.42
    Activation
    0.41
    Act Density 0.036%

    No Known Activations