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

    Neuronpedia

    INDEX
    Explanations

    Forum/discussion snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    odied
    -0.07
    净水
    -0.07
    ports
    -0.07
     commend
    -0.07
     correlations
    -0.07
     Valley
    -0.06
     LEDs
    -0.06
    .Field
    -0.06
     Gov
    -0.06
     Mods
    -0.06
    POSITIVE LOGITS
     sprayed
    0.08
    entries
    0.07
    "'↵
    0.07
     maternity
    0.07
     يجب
    0.07
    (userInfo
    0.07
    BASH
    0.07
     lr
    0.07
     Kimberly
    0.07
    提前
    0.07
    Act Density 0.060%

    No Known Activations