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
     tady
    -0.07
     diver
    -0.07
    ôm
    -0.07
     epoxy
    -0.06
     atr
    -0.06
     Concat
    -0.06
     Bott
    -0.06
     mez
    -0.06
    omer
    -0.06
     paren
    -0.06
    POSITIVE LOGITS
     Health
    0.15
     health
    0.13
    Health
    0.12
     HEALTH
    0.12
    .Health
    0.10
    health
    0.10
     wealth
    0.09
    _HEALTH
    0.08
    alth
    0.08
    -health
    0.08
    Act Density 0.045%

    No Known Activations