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

    Neuronpedia

    INDEX
    Explanations

    asm

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     setup
    -0.07
     hated
    -0.07
    003
    -0.07
     successful
    -0.07
     enemy
    -0.07
     "`
    -0.07
     issuer
    -0.06
    良い
    -0.06
    isbury
    -0.06
    500
    -0.06
    POSITIVE LOGITS
     Presenter
    0.07
     прим
    0.07
    utenberg
    0.06
     dbl
    0.06
    Hack
    0.06
     따른
    0.06
     Berg
    0.06
    .scroll
    0.06
    Drag
    0.06
     Chim
    0.06
    Act Density 0.004%

    No Known Activations