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

    Neuronpedia

    INDEX
    Explanations

    code special characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    95
    -0.08
    _AV
    -0.07
    .micro
    -0.06
    -ie
    -0.06
    CY
    -0.06
    แบ
    -0.06
    وغ
    -0.06
    947
    -0.06
    라피
    -0.06
    、この
    -0.06
    POSITIVE LOGITS
    .ship
    0.07
     electrode
    0.07
     revelation
    0.07
    .Safe
    0.07
     bracket
    0.07
     secrets
    0.06
    äm
    0.06
     chrono
    0.06
     loss
    0.06
    	table
    0.06
    Act Density 0.079%

    No Known Activations