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

    Neuronpedia

    INDEX
    Explanations

    were

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    22
    -0.07
    نة
    -0.06
     packages
    -0.06
     регулю
    -0.06
    率
    -0.06
     numbered
    -0.06
     coaches
    -0.06
     vertex
    -0.06
    \Test
    -0.06
    enticator
    -0.06
    POSITIVE LOGITS
    ("--------------------------------
    0.08
    /mp
    0.07
    italic
    0.07
    .bp
    0.06
    �
    0.06
    ,np
    0.06
     IMP
    0.06
     batting
    0.06
     topp
    0.06
     Iv
    0.06
    Act Density 0.062%

    No Known Activations