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

    Neuronpedia

    INDEX
    Explanations

    Self-introduction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	property
    -0.07
    _LEVEL
    -0.07
    DC
    -0.07
     hrá
    -0.06
     Giles
    -0.06
    stitutions
    -0.06
    hip
    -0.06
     Substance
    -0.06
    ogo
    -0.06
    Collapse
    -0.06
    POSITIVE LOGITS
    ในว
    0.07
    ‚
    0.06
     Edmonton
    0.06
     Emil
    0.06
     Зд
    0.06
    .spatial
    0.06
    }'.
    0.06
     ‌
    0.06
     excess
    0.06
     Εξ
    0.06
    Act Density 0.002%

    No Known Activations