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

    Neuronpedia

    INDEX
    Explanations

    were

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    般
    -0.06
     coment
    -0.06
    (simp
    -0.06
     thereby
    -0.06
    Compile
    -0.06
    τών
    -0.06
    Brun
    -0.06
    βολ
    -0.06
     sino
    -0.06
    (lon
    -0.06
    POSITIVE LOGITS
    Forge
    0.07
     motivated
    0.07
    جی
    0.06
     Residents
    0.06
    ACTION
    0.06
     Jag
    0.06
     Costs
    0.06
    arged
    0.06
    siz
    0.06
     Listening
    0.06
    Act Density 0.000%

    No Known Activations