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

    Neuronpedia

    INDEX
    Explanations

    generally allowed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     middleware
    0.45
     dismiss
    0.43
     Quelle
    0.43
     සං
    0.42
     Bridget
    0.41
     reggae
    0.41
     Presbyterian
    0.41
     Markus
    0.41
     dismissed
    0.40
     prévention
    0.40
    POSITIVE LOGITS
    व
    0.63
     edad
    0.55
    䒾
    0.53
     atractivo
    0.49
     inclin
    0.48
     mucho
    0.48
    ປີ
    0.47
    сила
    0.47
     sukar
    0.47
    ப்
    0.46
    Act Density 0.007%

    No Known Activations