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

    Neuronpedia

    INDEX
    Explanations

    against whom

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    amiseks
    0.39
    OSP
    0.38
    VHS
    0.38
    Rejected
    0.37
    гез
    0.37
    guides
    0.37
    --’
    0.37
     jusqu
    0.36
    ciato
    0.36
     akci
    0.36
    POSITIVE LOGITS
     vontade
    0.47
     rå
    0.46
     backdrop
    0.46
    rå
    0.46
     whom
    0.45
     विपरीत
    0.45
     railing
    0.44
     voluntad
    0.44
     volontà
    0.44
     Wills
    0.43
    Act Density 0.005%

    No Known Activations