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

    Neuronpedia

    INDEX
    Explanations

    under

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     relocation
    -0.07
     relocate
    -0.06
     nga
    -0.06
     fasta
    -0.06
    loha
    -0.06
     boj
    -0.06
     piracy
    -0.06
     qi
    -0.06
    poons
    -0.06
    :length
    -0.06
    POSITIVE LOGITS
     Under
    0.15
     under
    0.14
    Under
    0.13
     UNDER
    0.12
    under
    0.11
    -under
    0.10
    _under
    0.09
     underneath
    0.09
     onder
    0.09
     underst
    0.09
    Act Density 0.050%

    No Known Activations