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

    Neuronpedia

    INDEX
    Explanations

    mainly certainly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     also
    0.60
    also
    0.60
     myös
    0.58
     आल्सो
    0.57
    에도
    0.56
     также
    0.52
     också
    0.52
     ALSO
    0.52
    것도
    0.52
     également
    0.51
    POSITIVE LOGITS
     certainly
    0.74
     mainly
    0.70
    主要是
    0.66
    毕竟
    0.63
     głównie
    0.63
     principalmente
    0.61
     Mainly
    0.60
     hauptsächlich
    0.58
     Certainly
    0.58
    Certainly
    0.58
    Act Density 0.047%

    No Known Activations