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

    Neuronpedia

    INDEX
    Explanations

    comparative

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Motivation
    -1.04
     motivation
    -0.99
    Motivation
    -0.92
    practical
    -0.92
     Practical
    -0.91
     practical
    -0.90
    motivation
    -0.88
     motivación
    -0.84
    Practical
    -0.84
     ainfi
    -0.82
    POSITIVE LOGITS
    AndEndTag
    0.65
    ally
    0.54
    "}")
    0.54
     facie
    0.54
    ities
    0.50
     def
    0.50
    ised
    0.49
    ized
    0.48
    /**
    0.47
    ات
    0.46
    Act Density 0.051%

    No Known Activations