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

    Neuronpedia

    INDEX
    Explanations

    cell

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	l
    -0.07
     atmosphere
    -0.06
     HE
    -0.06
     repetition
    -0.06
    FT
    -0.06
    uilt
    -0.06
    sessions
    -0.06
     skeletons
    -0.06
    Literal
    -0.06
    ℃
    -0.06
    POSITIVE LOGITS
     surprise
    0.06
     significa
    0.06
    调整
    0.06
     JR
    0.06
    .until
    0.06
     změ
    0.06
     bypass
    0.06
    [out
    0.06
    SqlServer
    0.06
    (++
    0.06
    Act Density 0.036%

    No Known Activations