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

    Neuronpedia

    INDEX
    Explanations

    od

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     drowned
    -0.07
    ану
    -0.06
    .loc
    -0.06
    AK
    -0.06
     SEO
    -0.06
    /logging
    -0.06
    ERCHANT
    -0.06
    hire
    -0.06
    lw
    -0.06
    IED
    -0.06
    POSITIVE LOGITS
    synthesize
    0.08
    xlim
    0.07
     Rück
    0.07
     duż
    0.07
     scen
    0.07
    oolStrip
    0.07
     Domino
    0.07
     deque
    0.06
    ↵
↵
↵
    0.06
    ****************************************
    0.06
    Act Density 0.000%

    No Known Activations