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

    Neuronpedia

    INDEX
    Explanations

    Uncommon names or locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ocs
    -0.07
    Lewis
    -0.07
    ME
    -0.06
     occurs
    -0.06
    .getText
    -0.06
     governance
    -0.06
    auce
    -0.06
     çevres
    -0.06
     Phase
    -0.06
    >[
    -0.06
    POSITIVE LOGITS
    _PRI
    0.08
    quia
    0.07
    /native
    0.06
    iy
    0.06
     شو
    0.06
     huh
    0.06
    _empresa
    0.06
    _hidden
    0.06
    (dy
    0.06
     vraiment
    0.06
    Act Density 0.029%

    No Known Activations