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

    Neuronpedia

    INDEX
    Explanations

    Code/programming context

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     blackColor
    -0.07
    .getBy
    -0.07
     plt
    -0.06
    Amb
    -0.06
     :(
    -0.06
    」の
    -0.06
    AndGet
    -0.06
     Over
    -0.06
    xp
    -0.06
    >{
    -0.06
    POSITIVE LOGITS
     gost
    0.07
     hend
    0.07
     проп
    0.06
     pri
    0.06
     obsession
    0.06
    ніцип
    0.06
    depart
    0.06
     nj
    0.06
    essa
    0.06
    (ro
    0.06
    Act Density 0.031%

    No Known Activations