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

    Neuronpedia

    INDEX
    Explanations

    vegetarianism

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     itſelf
    -0.79
     Monfieur
    -0.78
     myſelf
    -0.76
     chrétienne
    -0.74
     feroit
    -0.72
    yards
    -0.71
     bezeichneter
    -0.71
    onuc
    -0.71
     vectorielle
    -0.71
    ergies
    -0.70
    POSITIVE LOGITS
     che
    0.56
     le
    0.52
    Cyfeiriadau
    0.50
    processData
    0.50
    หว่าง
    0.47
    ness
    0.46
     su
    0.46
     van
    0.46
     ComVisible
    0.45
    WriteBarrier
    0.44
    Act Density 0.039%

    No Known Activations