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

    Neuronpedia

    INDEX
    Explanations

    reps

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .patch
    -0.06
    Ak
    -0.06
    mtree
    -0.06
     estable
    -0.06
    _SUBJECT
    -0.06
    verbosity
    -0.06
     Deep
    -0.06
    Cor
    -0.06
    Else
    -0.06
    >"↵
    -0.06
    POSITIVE LOGITS
    лара
    0.08
    Ada
    0.07
     Trouble
    0.07
    dia
    0.07
     thư
    0.07
    ابل
    0.06
    .inv
    0.06
    дается
    0.06
     sug
    0.06
    	value
    0.06
    Act Density 0.000%

    No Known Activations