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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Timestamp
    -0.08
    .servers
    -0.07
    whel
    -0.07
    Lov
    -0.07
    .cli
    -0.06
     plá
    -0.06
    रल
    -0.06
    属
    -0.06
     stormed
    -0.06
    ˘
    -0.06
    POSITIVE LOGITS
    (true
    0.07
     petitions
    0.06
     різні
    0.06
    ída
    0.06
    cluding
    0.06
    idel
    0.06
     взя
    0.06
     requires
    0.06
     Matt
    0.06
     opaque
    0.06
    Act Density 0.000%

    No Known Activations