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

    Neuronpedia

    INDEX
    Explanations

    retina

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Elon
    -0.06
     endanger
    -0.06
    LowerCase
    -0.06
    lep
    -0.06
    psz
    -0.06
    -General
    -0.06
     poc
    -0.06
    	body
    -0.06
    ↓
    -0.06
    こそ
    -0.06
    POSITIVE LOGITS
     retina
    0.13
     Mata
    0.08
    _region
    0.07
     Tang
    0.07
    蒂
    0.07
    ì
    0.07
     reasoning
    0.07
     restriction
    0.07
     ти
    0.07
     preservation
    0.06
    Act Density 0.002%

    No Known Activations