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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /Page
    -0.08
    eturn
    -0.07
     dare
    -0.07
    𬣞
    -0.07
     edad
    -0.07
    .stamp
    -0.07
     wym
    -0.07
     Jahren
    -0.07
    /navigation
    -0.07
    qw
    -0.07
    POSITIVE LOGITS
    供
    0.08
     promotes
    0.07
    𐰼
    0.07
    thé
    0.07
    :{
↵
    0.06
     reserves
    0.06
    EO
    0.06
     glut
    0.06
    咸
    0.06
    ('.
    0.06
    Act Density 0.002%

    No Known Activations