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

    Neuronpedia

    INDEX
    Explanations

    narrative perspective choices

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     discontinue
    -0.09
    liers
    -0.09
     сентября
    -0.08
     viens
    -0.08
    .dispose
    -0.08
    -в
    -0.08
     дни
    -0.08
     явля
    -0.08
     February
    -0.08
     fevereiro
    -0.08
    POSITIVE LOGITS
     relatable
    0.08
     pron
    0.08
     illustrative
    0.08
    的话
    0.08
    shi
    0.08
     empathy
    0.08
     narr
    0.07
     الروا
    0.07
    uc
    0.07
     novels
    0.07
    Act Density 0.012%

    No Known Activations