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

    Neuronpedia

    INDEX
    Explanations

    greater than

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ру
    0.64
    }$.
    0.64
    ărilor
    0.61
    applic
    0.60
    ielles
    0.59
     فى
    0.59
    esthetics
    0.58
    0.58
    0.57
    unused
    0.57
    POSITIVE LOGITS
     resembling
    0.77
     zowel
    0.75
     doesn
    0.73
     Won
    0.72
     secures
    0.72
     zelf
    0.70
     Meer
    0.70
     greatly
    0.69
     resembles
    0.69
     både
    0.68
    Act Density 0.254%

    No Known Activations