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

    Neuronpedia

    INDEX
    Explanations

    reading code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Owen
    -0.07
    𐭊
    -0.07
    aty
    -0.07
    קומ
    -0.07
     Tom
    -0.07
     DAYS
    -0.07
    腆
    -0.07
    踏入
    -0.07
     Ker
    -0.07
    ENV
    -0.07
    POSITIVE LOGITS
    mun
    0.08
     füh
    0.07
    	L
    0.07
     eventual
    0.07
     cellphone
    0.07
     agosto
    0.07
    ria
    0.07
    -ce
    0.07
    trys
    0.07
    0.07
    Act Density 0.062%

    No Known Activations