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

    Neuronpedia

    INDEX
    Explanations

    back

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Any
    -0.08
    uien
    -0.07
    _UNDEFINED
    -0.07
    _EXPECT
    -0.07
    37
    -0.07
    elly
    -0.07
    erno
    -0.07
    esát
    -0.06
    .null
    -0.06
    ιδ
    -0.06
    POSITIVE LOGITS
     back
    0.13
     Back
    0.10
    -back
    0.09
     BACK
    0.09
    back
    0.09
    sett
    0.08
    	back
    0.07
     backwards
    0.07
    Back
    0.06
    回到
    0.06
    Act Density 0.025%

    No Known Activations