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

    Neuronpedia

    INDEX
    Explanations

    top concerns or challenges

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    urrencies
    -0.08
    .include
    -0.07
     devastating
    -0.07
    Components
    -0.07
    .Messages
    -0.06
     spiele
    -0.06
     gestures
    -0.06
     Kostenlos
    -0.06
    orrect
    -0.06
     Submission
    -0.06
    POSITIVE LOGITS
     vaguely
    0.07
     지정
    0.07
    _ud
    0.06
    ┴
    0.06
    ал
    0.06
    ağı
    0.06
     přesně
    0.06
     choisir
    0.06
     iw
    0.06
    赢
    0.06
    Act Density 0.008%

    No Known Activations