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

    Neuronpedia

    INDEX
    Explanations

    constructive feedback

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ga
    -0.08
    =document
    -0.07
    118
    -0.07
     button
    -0.07
     detect
    -0.07
     sizin
    -0.07
     hint
    -0.07
    神器
    -0.07
     ya
    -0.07
    ::*
    -0.07
    POSITIVE LOGITS
    RTR
    0.09
     rhetoric
    0.09
     actionable
    0.09
     поддержку
    0.09
    localized
    0.09
    Localized
    0.09
     constructive
    0.09
    (attribute
    0.09
     climate
    0.08
     concise
    0.08
    Act Density 0.009%

    No Known Activations