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

    Neuronpedia

    INDEX
    Explanations

    equals sign

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aussian
    -0.07
    efined
    -0.07
    Ionic
    -0.07
    :j
    -0.06
    :].
    -0.06
    elines
    -0.06
    роме
    -0.06
    859
    -0.06
    777
    -0.06
     IsPlainOldData
    -0.06
    POSITIVE LOGITS
     plá
    0.07
     Plum
    0.07
    _star
    0.07
    _tokens
    0.06
     лим
    0.06
     милли
    0.06
    (node
    0.06
    (dist
    0.06
     集
    0.06
     pošk
    0.06
    Act Density 0.100%

    No Known Activations