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

    Neuronpedia

    INDEX
    Explanations

    bowel movements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Uh
    -0.07
     reused
    -0.06
    aturdays
    -0.06
     confession
    -0.06
     MPI
    -0.06
    ensored
    -0.06
     Founded
    -0.06
     interrog
    -0.06
     BASE
    -0.06
     lawyer
    -0.06
    POSITIVE LOGITS
    .':
    0.06
     проп
    0.06
     비밀글
    0.06
    .Optional
    0.06
     consequential
    0.06
    计算
    0.06
     LESS
    0.06
     psycopg
    0.06
    천
    0.06
    -rated
    0.06
    Act Density 0.009%

    No Known Activations