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

    Neuronpedia

    INDEX
    Explanations

    brackets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ερμαν
    -0.06
    liğin
    -0.06
    W
    -0.06
     warranted
    -0.06
    ulsive
    -0.06
    ünde
    -0.06
     overweight
    -0.06
    ी↵
    -0.06
    M
    -0.06
    _population
    -0.06
    POSITIVE LOGITS
    dna
    0.07
     zum
    0.06
     promot
    0.06
    �
    0.06
    ::__
    0.06
    (fb
    0.06
    alt
    0.06
     '"';↵
    0.06
     strftime
    0.06
     scoff
    0.06
    Act Density 0.005%

    No Known Activations