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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    >Create
    -0.07
     rat
    -0.07
    ,",
    -0.07
     Hou
    -0.06
    ặp
    -0.06
    ",
    -0.06
    (",
    -0.06
    .Constant
    -0.06
     MBA
    -0.06
    CUSTOM
    -0.06
    POSITIVE LOGITS
    };
↵
↵
    0.07
     tweaks
    0.07
    _BITMAP
    0.07
    イク
    0.07
    -static
    0.06
    attention
    0.06
    angles
    0.06
    ()?;↵
    0.06
     คาส
    0.06
     мист
    0.06
    Act Density 0.014%

    No Known Activations