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

    Neuronpedia

    INDEX
    Explanations

    assembly/low-level branching

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     milyar
    -0.07
    oding
    -0.07
     Witness
    -0.06
    ogan
    -0.06
     nurturing
    -0.06
     Utah
    -0.06
     choking
    -0.06
    elsing
    -0.06
    318
    -0.06
     sprint
    -0.06
    POSITIVE LOGITS
    (('
    0.07
    olución
    0.06
    PY
    0.06
     změn
    0.06
     paperback
    0.06
     cá
    0.06
     messing
    0.06
    (template
    0.06
    wie
    0.06
     %"
    0.06
    Act Density 0.009%

    No Known Activations