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

    Neuronpedia

    INDEX
    Explanations

    exp

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ARENT
    -0.07
     너
    -0.07
    -host
    -0.07
     irresistible
    -0.07
     варі
    -0.07
     unilateral
    -0.07
     Stir
    -0.07
    ère
    -0.07
    .os
    -0.07
     sided
    -0.07
    POSITIVE LOGITS
     exp
    0.13
    exp
    0.12
    Exp
    0.11
    .exp
    0.09
     Exp
    0.09
    	exp
    0.09
     EXP
    0.09
    -exp
    0.09
    /exp
    0.09
    (exp
    0.09
    Act Density 0.012%

    No Known Activations