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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    shine
    -0.07
     sab
    -0.07
     hallway
    -0.07
    み
    -0.06
    ़ा
    -0.06
    enumerate
    -0.06
     savun
    -0.06
    ักร
    -0.06
    UTC
    -0.06
    reten
    -0.06
    POSITIVE LOGITS
    ]?
    0.07
    编辑
    0.07
     rescue
    0.07
     nominate
    0.07
    核
    0.06
     unpredict
    0.06
    _super
    0.06
    _Value
    0.06
    oto
    0.06
     permitting
    0.06
    Act Density 0.000%

    No Known Activations