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

    Neuronpedia

    INDEX
    Explanations

    Combinatorial computations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Pulse
    -0.08
     Pulse
    -0.08
     hypocrisy
    -0.08
    рок
    -0.08
    osur
    -0.08
     suspect
    -0.08
     phòng
    -0.07
     gy
    -0.07
    (Route
    -0.07
    Clause
    -0.07
    POSITIVE LOGITS
     রেখে
    0.08
     exhaustive
    0.08
     ಬಿಡ
    0.08
     Suomessa
    0.08
     nona
    0.08
     antaa
    0.07
     explosive
    0.07
     extrac
    0.07
    Empty
    0.07
     expl
    0.07
    Act Density 0.008%

    No Known Activations