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

    Neuronpedia

    INDEX
    Explanations

    Llama resources access

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     petting
    0.67
    Bloomberg
    0.58
    라이언
    0.57
    ន៍
    0.57
     Bloomberg
    0.57
     Bürgermeister
    0.57
    <unused284>
    0.56
    ंबकीय
    0.56
     fwrite
    0.56
    nashville
    0.56
    POSITIVE LOGITS
    posta
    0.68
     sinusoidal
    0.59
    post
    0.59
     Post
    0.58
    point
    0.57
     verifica
    0.57
     posta
    0.57
     bar
    0.57
     आकार
    0.56
    Post
    0.56
    Act Density 0.001%

    No Known Activations