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

    Neuronpedia

    INDEX
    Explanations

    Medical diagnoses and patients

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     decline
    -0.07
    rada
    -0.07
    .k
    -0.06
    gy
    -0.06
     тради
    -0.06
    rotate
    -0.06
     row
    -0.06
    _verify
    -0.06
     merit
    -0.06
    _mes
    -0.06
    POSITIVE LOGITS
     ASF
    0.07
     πε
    0.06
    ском
    0.06
    AU
    0.06
     жил
    0.06
    meldung
    0.06
     Clin
    0.06
     PAR
    0.06
     ironically
    0.06
    eof
    0.06
    Act Density 0.066%

    No Known Activations