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

    Neuronpedia

    INDEX
    Explanations

    progressive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bard
    -0.07
    plet
    -0.07
    �
    -0.06
     ':
    -0.06
    YO
    -0.06
    aná
    -0.06
     هوش
    -0.06
     Resets
    -0.06
     Ke
    -0.06
     hd
    -0.06
    POSITIVE LOGITS
     progressive
    0.09
     gro
    0.07
    -trans
    0.07
     physiological
    0.07
    的地
    0.07
    ordinator
    0.06
     Michelle
    0.06
    ư
    0.06
    专
    0.06
     adaptive
    0.06
    Act Density 0.002%

    No Known Activations