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

    Neuronpedia

    INDEX
    Explanations

    second thought

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    atos
    -0.07
    amodel
    -0.07
    单位
    -0.06
    AWS
    -0.06
    าฟ
    -0.06
    OL
    -0.06
    ливих
    -0.06
    enha
    -0.06
    odafone
    -0.06
    acionales
    -0.06
    POSITIVE LOGITS
     honour
    0.07
     *)↵
    0.06
     Modeling
    0.06
     Roberts
    0.06
     Republican
    0.06
    urchase
    0.06
    ))/
    0.06
     keen
    0.06
    реп
    0.06
     separates
    0.06
    Act Density 0.039%

    No Known Activations