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

    Neuronpedia

    INDEX
    Explanations

    47

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    xiv
    -0.07
    4
    -0.06
     zus
    -0.06
    ================
    -0.06
    _CONSOLE
    -0.06
     Morales
    -0.06
    -collapse
    -0.06
     isl
    -0.06
     allergy
    -0.06
    zet
    -0.06
    POSITIVE LOGITS
     Fame
    0.06
     Round
    0.06
    <Color
    0.06
     """.
    0.06
    779
    0.06
    (Debug
    0.06
     completeness
    0.06
     spiritually
    0.06
    liquid
    0.06
     Args
    0.06
    Act Density 0.000%

    No Known Activations