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

    Neuronpedia

    INDEX
    Explanations

    ="

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    @show
    -0.08
    ↵                        ↵
    -0.07
     nurturing
    -0.07
    ()));
↵
    -0.07
    .Created
    -0.07
    )";
↵
    -0.07
    ">↵↵↵
    -0.06
    '),↵↵
    -0.06
    :(
    -0.06
    ↵      ↵
    -0.06
    POSITIVE LOGITS
     صالح
    0.08
    ーパ
    0.06
     چاپ
    0.06
    ีด
    0.06
    nard
    0.06
    ่าม
    0.06
    _ATOM
    0.06
    -has
    0.06
    agher
    0.06
    xCB
    0.06
    Act Density 0.006%

    No Known Activations