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

    Neuronpedia

    INDEX
    Explanations

    Conversational writing style

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pořad
    -0.08
     prism
    -0.07
    apture
    -0.07
     ≈
    -0.07
     багать
    -0.06
     سپس
    -0.06
    κα
    -0.06
     سوم
    -0.06
    (fieldName
    -0.06
     пог
    -0.06
    POSITIVE LOGITS
    bral
    0.07
    Prof
    0.07
     MILF
    0.07
     Rough
    0.07
     rst
    0.06
     Residents
    0.06
    Voice
    0.06
    tero
    0.06
    uffed
    0.06
    tober
    0.06
    Act Density 0.048%

    No Known Activations