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

    Neuronpedia

    INDEX
    Explanations

    able

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tightened
    -0.08
     fw
    -0.06
     rele
    -0.06
    composite
    -0.06
     hac
    -0.06
     easily
    -0.06
     raids
    -0.06
     complexities
    -0.06
    िण
    -0.06
     afraid
    -0.06
    POSITIVE LOGITS
     unpopular
    0.06
    625
    0.06
    checks
    0.06
     edits
    0.06
    (library
    0.06
     食
    0.06
    ","
    0.06
     Jad
    0.06
    Branch
    0.06
    .setImageResource
    0.06
    Act Density 0.002%

    No Known Activations