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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =""
    -0.06
     Chat
    -0.06
     thrive
    -0.06
     gives
    -0.06
     shifts
    -0.06
    Patient
    -0.06
     give
    -0.06
     unreliable
    -0.06
    leads
    -0.06
    Looks
    -0.06
    POSITIVE LOGITS
     fruition
    0.06
    roje
    0.06
     Millenn
    0.06
    .poster
    0.06
     اتحاد
    0.06
    ليه
    0.06
    .touches
    0.06
    pk
    0.06
    ำ
    0.06
    ่อไป
    0.06
    Act Density 0.354%

    No Known Activations