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

    Neuronpedia

    INDEX
    Explanations

    Health

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rodrig
    -0.08
    idar
    -0.08
    948
    -0.08
    аем
    -0.07
     cop
    -0.07
     Circular
    -0.07
     dime
    -0.07
    8
    -0.07
    48
    -0.07
     cyclic
    -0.07
    POSITIVE LOGITS
     Health
    0.22
     health
    0.20
    Health
    0.16
     HEALTH
    0.15
    health
    0.14
    -health
    0.12
    .Health
    0.12
    _HEALTH
    0.11
    .health
    0.09
     Healthy
    0.09
    Act Density 0.042%

    No Known Activations