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

    Neuronpedia

    INDEX
    Explanations

    question marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     durante
    -0.07
    、お
    -0.07
    怖
    -0.07
     Wochen
    -0.07
     这
    -0.06
     tady
    -0.06
     име
    -0.06
    _FAILURE
    -0.06
    Daily
    -0.06
     الأ
    -0.06
    POSITIVE LOGITS
    submenu
    0.07
     receive
    0.06
    .prompt
    0.06
    case
    0.06
     rendition
    0.06
     Snyder
    0.06
     metrics
    0.06
     concept
    0.06
    (Conv
    0.06
    .values
    0.06
    Act Density 0.020%

    No Known Activations