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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Task
    -0.06
     '&'
    -0.06
    (cursor
    -0.06
     cres
    -0.06
     культу
    -0.06
    zcze
    -0.06
    _box
    -0.06
    rippling
    -0.06
    	trace
    -0.06
    香
    -0.06
    POSITIVE LOGITS
     interventions
    0.08
    amera
    0.07
     munch
    0.07
    ôm
    0.07
     sweetheart
    0.07
    stood
    0.07
     mL
    0.06
     و
    0.06
    бут
    0.06
    .DataTable
    0.06
    Act Density 0.010%

    No Known Activations