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

    Neuronpedia

    INDEX
    Explanations

    language and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ይህ
    0.36
     halten
    0.36
    пят
    0.36
    ुकी
    0.36
     Beside
    0.35
    afe
    0.35
    gtk
    0.35
    Nowadays
    0.35
     siguiendo
    0.35
     Cinque
    0.35
    POSITIVE LOGITS
     laoreet
    0.40
     камень
    0.40
    done
    0.39
     분류
    0.39
    Connor
    0.39
    ignment
    0.38
    Ĥ
    0.38
     gamanam
    0.38
     zhong
    0.38
    zhong
    0.38
    Act Density 0.001%

    No Known Activations