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

    Neuronpedia

    INDEX
    Explanations

    dates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    756
    -0.07
     böyle
    -0.06
    cdb
    -0.06
     winger
    -0.06
    71
    -0.06
    inema
    -0.06
    ####
    -0.06
     blonde
    -0.06
    네
    -0.06
    213
    -0.06
    POSITIVE LOGITS
    flip
    0.08
     Hurt
    0.07
     दर
    0.07
    ="">↵
    0.07
    ียรต
    0.07
     shutting
    0.07
    ;?></
    0.07
    endl
    0.06
     assault
    0.06
     запит
    0.06
    Act Density 0.063%

    No Known Activations