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

    Neuronpedia

    INDEX
    Explanations

    Love

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     orde
    -0.08
     erzeug
    -0.07
     geschaffen
    -0.07
     Comparing
    -0.07
    walk
    -0.07
    Interpolation
    -0.07
     Klima
    -0.07
     વેપ
    -0.07
     Hö
    -0.07
     GBR
    -0.07
    POSITIVE LOGITS
     struggles
    0.08
     unsuccess
    0.08
     struggled
    0.08
     Jal
    0.08
    igslist
    0.08
    nesia
    0.08
     Celebrity
    0.08
    .music
    0.08
     celebrity
    0.08
    .controllers
    0.08
    Act Density 0.030%

    No Known Activations