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

    Neuronpedia

    INDEX
    Explanations

    what

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _SUCCESS
    -0.08
    kar
    -0.07
     senin
    -0.07
     inds
    -0.07
     �
    -0.07
    督
    -0.07
    .showError
    -0.07
     Tanner
    -0.07
    辛
    -0.07
    ISOString
    -0.07
    POSITIVE LOGITS
     what
    0.09
    I
    0.07
     THAT
    0.06
     how
    0.06
    */↵
    0.06
     distinctly
    0.06
     hue
    0.06
     thanking
    0.06
    .literal
    0.06
     that
    0.06
    Act Density 0.032%

    No Known Activations