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

    Neuronpedia

    INDEX
    Explanations

    7B models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ～
    0.94
    हान
    0.74
    京
    0.73
    ，
    0.72
    北京市
    0.72
    decorate
    0.71
     ，
    0.70
     عظیم
    0.70
    【
    0.69
     الر
    0.69
    POSITIVE LOGITS
     മത
    0.83
     prompt
    0.79
     mentored
    0.78
     Prompt
    0.77
     marquée
    0.75
     pasta
    0.75
     transcription
    0.73
     Mantra
    0.73
     rapat
    0.73
     lids
    0.72
    Act Density 0.038%

    No Known Activations