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

    Neuronpedia

    INDEX
    Explanations

    arXiv papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .orange
    -0.07
     Britann
    -0.06
    .getDocument
    -0.06
     adaptation
    -0.06
     celý
    -0.06
    eşit
    -0.06
    chg
    -0.06
     fragmentation
    -0.06
    banana
    -0.06
    .;.;
    -0.06
    POSITIVE LOGITS
    xing
    0.07
    //[
    0.07
     Ac
    0.07
     Israelis
    0.07
    _TRANSFER
    0.07
    ev
    0.06
    intval
    0.06
     Ordering
    0.06
    juries
    0.06
    OneToMany
    0.06
    Act Density 0.001%

    No Known Activations