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

    Neuronpedia

    INDEX
    Explanations

    my honor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     questions
    0.46
     alimony
    0.43
     Asking
    0.41
     slamming
    0.41
     slams
    0.41
     asking
    0.40
     shen
    0.40
    Asking
    0.40
    osis
    0.40
     evil
    0.39
    POSITIVE LOGITS
     médiocrement
    0.37
    seguir
    0.37
    ocop
    0.36
    醯
    0.35
    മ്മി
    0.35
    再び
    0.35
    猢
    0.35
    螟
    0.34
    ocat
    0.34
    Importer
    0.34
    Act Density 0.000%

    No Known Activations