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

    Neuronpedia

    INDEX
    Explanations

    Here's introducing an explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     attracted
    0.74
     emitted
    0.72
    করণ
    0.72
     influenced
    0.70
              
    0.69
     undermined
    0.69
            
    0.68
    ;
    0.67
     achieved
    0.67
     postponed
    0.67
    POSITIVE LOGITS
    ﺎ
    0.84
    да
    0.80
    swering
    0.79
    rscheinlich
    0.76
    umoto
    0.76
    َل
    0.76
    alnya
    0.76
    ljivo
    0.72
    ším
    0.71
    ıl
    0.70
    Act Density 0.029%

    No Known Activations