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

    Neuronpedia

    INDEX
    Explanations

    console input prompts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    انة
    0.66
    ارين
    0.64
    жала
    0.64
    стите
    0.63
     Printers
    0.61
    aise
    0.60
    zant
    0.59
    ţii
    0.59
    igkeits
    0.59
    ды
    0.58
    POSITIVE LOGITS
     cryptocurrency
    0.66
     pandemic
    0.62
     וא
    0.61
     kondisi
    0.59
     pozi
    0.59
     süreç
    0.59
     i
    0.58
     www
    0.58
     condi
    0.58
     ubic
    0.57
    Act Density 0.002%

    No Known Activations