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

    Neuronpedia

    INDEX
    Explanations

    open

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hormonal
    -0.08
    gum
    -0.08
     Gum
    -0.08
     fruct
    -0.07
    เซีย
    -0.07
    ufu
    -0.07
     origine
    -0.07
     ць
    -0.07
    ಾರು
    -0.07
     വര
    -0.07
    POSITIVE LOGITS
     counterpart
    0.08
     entitled
    0.08
    kill
    0.07
     nicer
    0.07
     உறுப்ப
    0.07
     Conservative
    0.07
    <Unit
    0.07
    ดี
    0.07
     representatives
    0.07
     desirable
    0.07
    Act Density 0.004%

    No Known Activations