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

    Neuronpedia

    INDEX
    Explanations

    New

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    itta
    -0.07
     Elliott
    -0.07
    capt
    -0.07
    ...">↵
    -0.07
     ',
    -0.07
     поба
    -0.07
     dni
    -0.06
    .ci
    -0.06
     circumstances
    -0.06
    ssc
    -0.06
    POSITIVE LOGITS
     New
    0.20
    New
    0.17
     NEW
    0.13
     new
    0.13
    NEW
    0.11
    new
    0.11
    .New
    0.11
    /New
    0.10
    -New
    0.10
    _New
    0.09
    Act Density 0.113%

    No Known Activations