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

    Neuronpedia

    INDEX
    Explanations

    language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    opt
    -0.08
     LOVE
    -0.06
    ████
    -0.06
    .read
    -0.06
     compile
    -0.06
    value
    -0.06
    烦
    -0.06
     Car
    -0.06
    _EPS
    -0.06
    ाव
    -0.06
    POSITIVE LOGITS
    "]
↵
    0.07
    **
↵
    0.06
    ères
    0.06
    یره
    0.06
    BSD
    0.06
    builders
    0.06
    _#{
    0.06
     expansive
    0.06
     Lt
    0.06
     Omega
    0.06
    Act Density 0.040%

    No Known Activations