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

    Neuronpedia

    INDEX
    Explanations

    XML contexts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -insert
    -0.07
    =sub
    -0.06
     minY
    -0.06
     meet
    -0.06
     sliders
    -0.06
    /repos
    -0.06
     canned
    -0.06
    .sat
    -0.06
    iman
    -0.06
    .help
    -0.06
    POSITIVE LOGITS
     ослож
    0.07
    �
    0.06
     пу
    0.06
     rus
    0.06
    IV
    0.06
    mund
    0.06
    VES
    0.06
     jetzt
    0.06
     ){
↵
    0.06
    FLAGS
    0.06
    Act Density 0.005%

    No Known Activations