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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    화
    -0.08
     Holm
    -0.08
     часу
    -0.08
     namun
    -0.08
    voli
    -0.07
    letic
    -0.07
     wrongly
    -0.07
    甚至
    -0.07
    ahal
    -0.07
     smartphone
    -0.07
    POSITIVE LOGITS
    Established
    0.09
     Established
    0.08
     established
    0.08
     দুটি
    0.08
     etabl
    0.08
     entendre
    0.08
    Animating
    0.08
     estabelecer
    0.08
    Equation
    0.08
     intento
    0.08
    Act Density 0.036%

    No Known Activations