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

    Neuronpedia

    INDEX
    Explanations

    names after named

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    zens
    -0.09
     Wer
    -0.09
    _CMP
    -0.09
     Wong
    -0.09
    ayers
    -0.08
    intree
    -0.08
    /legal
    -0.08
     hipp
    -0.08
    vern
    -0.08
    ä¸īä¸ī
    -0.08
    POSITIVE LOGITS
     Mist
    0.13
     oblig
    0.12
     mist
    0.12
     Brandon
    0.11
     Vin
    0.10
     Bands
    0.10
    oldem
    0.10
     Hutch
    0.10
     steel
    0.10
     Dal
    0.10
    Act Density 0.030%

    No Known Activations