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
     ery
    -0.07
     relatively
    -0.07
    -types
    -0.07
     Measure
    -0.07
    ching
    -0.07
    Subtitle
    -0.06
     Reconstruction
    -0.06
    rikes
    -0.06
     fing
    -0.06
     bridge
    -0.06
    POSITIVE LOGITS
    _pix
    0.06
     slashed
    0.06
     Jewel
    0.06
    ilion
    0.06
     жовт
    0.06
     kapsam
    0.06
     Sesso
    0.06
    _Location
    0.06
    orraine
    0.06
     unrest
    0.06
    Act Density 0.083%

    No Known Activations