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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uxxxx
    -0.72
     estimés
    -0.61
    +#+#
    -0.57
    ArgsConstructor
    -0.56
    SOUNDBITE
    -0.55
    Rhestr
    -0.53
     <<<<<<<<<<<<<<
    -0.52
     continuant
    -0.52
    AddTagHelper
    -0.52
    endphp
    -0.52
    POSITIVE LOGITS
     he
    0.59
     Administrativna
    0.59
    He
    0.55
     some
    0.51
     He
    0.51
    enumi
    0.50
     محفوظة
    0.49
     His
    0.48
     regolare
    0.47
     rien
    0.46
    Act Density 0.001%

    No Known Activations