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

    Neuronpedia

    INDEX
    Explanations

    articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rumors
    -0.07
    .:
    -0.07
    anned
    -0.07
    imate
    -0.07
     projection
    -0.07
    에
    -0.07
     bombers
    -0.07
     DOMAIN
    -0.07
     "~/
    -0.07
     recruiter
    -0.06
    POSITIVE LOGITS
     محل
    0.07
    before
    0.06
    _vis
    0.06
    ης
    0.06
     음악
    0.06
    velle
    0.06
     उद
    0.06
    bew
    0.06
     abide
    0.06
    .prof
    0.06
    Act Density 0.000%

    No Known Activations