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

    Neuronpedia

    INDEX
    Explanations

    Middle

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _arr
    -0.07
     Wer
    -0.07
    craft
    -0.07
    daughter
    -0.07
    Wer
    -0.06
     bus
    -0.06
    _CTL
    -0.06
    aguay
    -0.06
    AGMA
    -0.06
     RES
    -0.06
    POSITIVE LOGITS
    composed
    0.07
    ingular
    0.07
     graded
    0.06
     Silicon
    0.06
    Suggestions
    0.06
     Shortcut
    0.06
     getToken
    0.06
    square
    0.06
    면서
    0.06
     güncel
    0.06
    Act Density 0.003%

    No Known Activations