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

    Neuronpedia

    INDEX
    Explanations

    cause and effect

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     robots
    -0.08
    apos
    -0.06
    .ga
    -0.06
    тро
    -0.06
    \\"
    -0.06
     spy
    -0.06
    `;
    -0.06
    ertools
    -0.06
     bq
    -0.06
    ilerine
    -0.06
    POSITIVE LOGITS
     γυνα
    0.07
     sensory
    0.07
    .ErrorCode
    0.06
     missed
    0.06
     některé
    0.06
    أم
    0.06
    ยา
    0.06
     rhe
    0.06
     worsh
    0.06
    ----------
↵
    0.06
    Act Density 0.097%

    No Known Activations