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

    Neuronpedia

    INDEX
    Explanations

    3

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ��
    -0.06
    飯
    -0.06
    avenous
    -0.06
     Pemb
    -0.06
     (“
    -0.06
     zv
    -0.06
     forensic
    -0.06
    oven
    -0.06
     Cần
    -0.06
    _failed
    -0.06
    POSITIVE LOGITS
    3
    0.07
    '%
    0.07
    UNICATION
    0.07
     utmost
    0.07
    _OVERRIDE
    0.06
    Themes
    0.06
     Concepts
    0.06
     крит
    0.06
     tribute
    0.06
     STRUCT
    0.06
    Act Density 0.005%

    No Known Activations