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

    Neuronpedia

    INDEX
    Explanations

    legacy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hut
    -0.07
     علم
    -0.07
     색
    -0.07
     pulled
    -0.06
     Robert
    -0.06
    _In
    -0.06
     spelling
    -0.06
    Viewer
    -0.06
    로운
    -0.06
    	pool
    -0.06
    POSITIVE LOGITS
     Legacy
    0.11
    Legacy
    0.09
     legacy
    0.09
     qty
    0.07
    legacy
    0.07
    .static
    0.07
     wake
    0.07
    .Core
    0.07
     mmc
    0.07
    ๑
    0.07
    Act Density 0.003%

    No Known Activations