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

    Neuronpedia

    INDEX
    Explanations

    wondering

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    _assigned
    -0.07
    anco
    -0.07
    .visit
    -0.07
    atalog
    -0.07
    签
    -0.07
    تأكد
    -0.07
    tell
    -0.07
    ()}</
    -0.06
     contrato
    -0.06
    POSITIVE LOGITS
    멂
    0.07
     Laundry
    0.07
    小さな
    0.07
    퓪
    0.06
    𝓃
    0.06
    随
    0.06
     smtp
    0.06
     playground
    0.06
    が
    0.06
     plumbing
    0.06
    Act Density 0.014%

    No Known Activations