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

    Neuronpedia

    INDEX
    Explanations

    J

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .SimpleButton
    -0.08
    -agent
    -0.07
    Collision
    -0.06
     hvad
    -0.06
    .ITEM
    -0.06
    иту
    -0.06
    เพ
    -0.06
    ecret
    -0.06
    AMP
    -0.06
     surplus
    -0.06
    POSITIVE LOGITS
    ‬
    0.07
     veil
    0.07
     Nathan
    0.07
    �
    0.07
     filming
    0.06
     переп
    0.06
    เคร
    0.06
    0.06
     body
    0.06
     extracting
    0.06
    Act Density 0.006%

    No Known Activations