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

    Neuronpedia

    INDEX
    Explanations

    Mar words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TARGET
    0.86
    ential
    0.86
     Target
    0.83
    Target
    0.80
     magari
    0.79
     varying
    0.77
    Bye
    0.76
    的目标
    0.71
    hedral
    0.71
     nl
    0.71
    POSITIVE LOGITS
    smanship
    1.04
     часу
    0.91
    iposa
    0.91
    mallow
    0.89
    igold
    0.88
    ধর
    0.86
    riott
    0.85
    ्वल
    0.85
    шал
    0.84
    chetti
    0.84
    Act Density 0.072%

    No Known Activations