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

    Neuronpedia

    INDEX
    Explanations

    Technical language, code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _PARENT
    -0.07
     trainer
    -0.07
    magnitude
    -0.07
    .command
    -0.07
     организации
    -0.06
    ="
    -0.06
    .au
    -0.06
    entered
    -0.06
     Forest
    -0.06
     CONSTANTS
    -0.06
    POSITIVE LOGITS
    。(
    0.07
     tvor
    0.06
     nghiệ
    0.06
     spills
    0.06
    اخته
    0.06
    ρό
    0.06
     듯
    0.06
     subpoena
    0.06
     mimeType
    0.06
    (commit
    0.06
    Act Density 0.337%

    No Known Activations