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

    Neuronpedia

    INDEX
    Explanations

    Snippets of text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Eug
    -0.07
    _ENC
    -0.06
    ])/
    -0.06
     più
    -0.06
     anticipation
    -0.06
    ensex
    -0.06
    mid
    -0.06
     Rab
    -0.06
     �
    -0.06
     hasta
    -0.06
    POSITIVE LOGITS
     Renew
    0.08
    -J
    0.07
     buộc
    0.06
    引き
    0.06
     [=[
    0.06
    arks
    0.06
    Florida
    0.06
    Saving
    0.06
     reward
    0.06
    ining
    0.06
    Act Density 0.000%

    No Known Activations