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

    Neuronpedia

    INDEX
    Explanations

    but

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    UTTON
    -0.09
    iehen
    -0.08
     dada
    -0.08
     fend
    -0.08
     вдруг
    -0.08
    amọ
    -0.08
    neos
    -0.08
    amiques
    -0.08
    升
    -0.08
    mages
    -0.08
    POSITIVE LOGITS
     caution
    0.09
     причем
    0.08
     cautious
    0.08
     albeit
    0.08
     Voraussetzung
    0.08
     Ai
    0.08
     желательно
    0.07
     Beware
    0.07
     careful
    0.07
     bathtub
    0.07
    Act Density 0.025%

    No Known Activations