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

    Neuronpedia

    INDEX
    Explanations

    code, instructions, general text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Agility
    -0.07
     addicted
    -0.06
    ์ก
    -0.06
     ENV
    -0.06
     Rw
    -0.06
     COLUMN
    -0.06
    =str
    -0.06
     Hy
    -0.05
     nost
    -0.05
     nar
    -0.05
    POSITIVE LOGITS
    alternate
    0.07
     brainstorm
    0.06
    seven
    0.06
    Jonathan
    0.06
     enforced
    0.06
     absorption
    0.06
     århus
    0.06
     교육
    0.06
     acquaintance
    0.06
    .groupBox
    0.06
    Act Density 0.000%

    No Known Activations