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

    Neuronpedia

    INDEX
    Explanations

    cannot be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     عارفين
    0.52
     قادر
    0.49
    知道
    0.49
     able
    0.47
     imagining
    0.46
     сможете
    0.46
     смогли
    0.44
    imagine
    0.44
     tahu
    0.44
     Able
    0.43
    POSITIVE LOGITS
     be
    0.73
     coexist
    0.58
     exist
    0.51
     იყოს
    0.50
     brukes
    0.48
     быть
    0.48
     essere
    0.48
     باشد
    0.47
     occur
    0.47
     arise
    0.46
    Act Density 0.006%

    No Known Activations