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

    Neuronpedia

    INDEX
    Explanations

    skin

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Basically
    -0.07
    adem
    -0.07
    Basically
    -0.07
    메
    -0.07
     Campus
    -0.07
    :])
    -0.07
    ंब
    -0.06
    ैद
    -0.06
     skepticism
    -0.06
     устан
    -0.06
    POSITIVE LOGITS
     tonic
    0.07
     trembling
    0.06
    	ASSERT
    0.06
    =get
    0.06
     Relief
    0.06
    iska
    0.06
    (true
    0.06
    Not
    0.06
    /Y
    0.06
    组织
    0.06
    Act Density 0.000%

    No Known Activations