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

    Neuronpedia

    INDEX
    Explanations

    non-English

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Crack
    -0.06
    }[
    -0.06
    _tweet
    -0.06
     Phaser
    -0.06
     ”↵
    -0.06
    kovou
    -0.06
    .strptime
    -0.06
    Margins
    -0.06
     Теп
    -0.06
    textbox
    -0.06
    POSITIVE LOGITS
    ("./
    0.07
     condolences
    0.06
    .tb
    0.06
    ongo
    0.06
     stern
    0.06
     количество
    0.06
    ありがとうござ
    0.06
    σταν
    0.06
    oger
    0.06
    ugi
    0.06
    Act Density 0.036%

    No Known Activations