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

    Neuronpedia

    INDEX
    Explanations

    distress

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Seminar
    -0.07
    تحرك
    -0.07
     gasoline
    -0.07
     complaint
    -0.07
     jong
    -0.07
    .fe
    -0.07
    êt
    -0.07
    _free
    -0.06
    efd
    -0.06
     mudança
    -0.06
    POSITIVE LOGITS
     perpetrators
    0.07
    .animations
    0.07
    ORM
    0.07
    怀
    0.06
    -------------
    0.06
    _VC
    0.06
    筹
    0.06
     Guy
    0.06
    亮丽
    0.06
     FTP
    0.06
    Act Density 0.009%

    No Known Activations