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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	service
    -0.07
     userdata
    -0.07
     Como
    -0.07
     Jelly
    -0.07
     obstruction
    -0.06
     '"
    -0.06
    sgiving
    -0.06
    905
    -0.06
    同步
    -0.06
    }")]↵
    -0.06
    POSITIVE LOGITS
     tantal
    0.06
    development
    0.06
    Crystal
    0.06
    άλ
    0.06
    intage
    0.06
     latina
    0.06
    _CLAMP
    0.06
    오는
    0.06
    #line
    0.06
     curled
    0.06
    Act Density 0.046%

    No Known Activations