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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Repository
    -0.06
    =%.
    -0.06
    Information
    -0.06
    孙
    -0.06
     ingredient
    -0.06
    tokens
    -0.06
    ครบ
    -0.06
    .ResponseWriter
    -0.06
     Ρ
    -0.05
    чил
    -0.05
    POSITIVE LOGITS
     Lara
    0.08
     SCE
    0.08
     Camera
    0.07
    brightness
    0.07
     backbone
    0.07
    Simply
    0.07
    erek
    0.07
    Forget
    0.07
     motions
    0.06
     disob
    0.06
    Act Density 0.000%

    No Known Activations