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

    Neuronpedia

    INDEX
    Explanations

    dieting and food

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ae
    -0.07
     relational
    -0.06
    Conta
    -0.06
    彼女
    -0.06
    onde
    -0.06
    (e
    -0.06
     wealthy
    -0.06
    _THREADS
    -0.06
    .strings
    -0.06
     wells
    -0.06
    POSITIVE LOGITS
    州市
    0.06
     случ
    0.06
     Pasta
    0.06
    范
    0.06
     Savaş
    0.06
     růz
    0.06
     भग
    0.06
    Used
    0.06
    typescript
    0.06
    .uml
    0.06
    Act Density 0.040%

    No Known Activations