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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tumb
    -0.09
    _RUNNING
    -0.09
    _running
    -0.09
    immut
    -0.08
    ायला
    -0.08
     invokes
    -0.08
     clen
    -0.08
     piling
    -0.08
    认真
    -0.07
    =(-
    -0.07
    POSITIVE LOGITS
     irrelevant
    0.10
     exclude
    0.09
     unrelated
    0.09
    technical
    0.08
     overly
    0.08
    ot
    0.08
     technical
    0.08
     obvious
    0.08
     occasional
    0.08
    ottery
    0.08
    Act Density 0.014%

    No Known Activations