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

    Neuronpedia

    INDEX
    Explanations

    apologize

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (weights
    -0.07
    Compatibility
    -0.06
     CircularProgressIndicator
    -0.06
     втор
    -0.06
     imp
    -0.06
     "</
    -0.06
    lardan
    -0.06
     getter
    -0.06
     {}".
    -0.06
     stringValue
    -0.06
    POSITIVE LOGITS
     apologize
    0.08
     lẽ
    0.08
    rol
    0.07
    όδ
    0.07
     قول
    0.07
     apologise
    0.07
     पहल
    0.06
     unfolded
    0.06
     اقدام
    0.06
    ΠΑ
    0.06
    Act Density 0.007%

    No Known Activations