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

    Neuronpedia

    INDEX
    Explanations

    generic solutions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    map
    -0.07
    _cu
    -0.07
    rock
    -0.07
     Webb
    -0.06
    Bell
    -0.06
     ngược
    -0.06
    рож
    -0.06
     Bell
    -0.06
     Workspace
    -0.06
    _HASH
    -0.06
    POSITIVE LOGITS
     Weiter
    0.07
     lawful
    0.06
    (Display
    0.06
    _SECONDS
    0.06
     detrimental
    0.06
     أمريكي
    0.06
    μερα
    0.06
     womb
    0.06
     매매
    0.06
     قتل
    0.06
    Act Density 0.073%

    No Known Activations