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

    Neuronpedia

    INDEX
    Explanations

    information

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    sez
    -0.06
    Fuck
    -0.06
     אותה
    -0.06
    idental
    -0.06
    ldb
    -0.06
    onica
    -0.06
     Samoa
    -0.06
    яем
    -0.06
    Implicit
    -0.06
     lieutenant
    -0.06
    POSITIVE LOGITS
    RadioButton
    0.07
    犹如
    0.07
    =request
    0.07
    (platform
    0.07
    .template
    0.07
    岐
    0.07
     dereg
    0.07
    等多种
    0.07
     promotions
    0.07
     refers
    0.07
    Act Density 0.028%

    No Known Activations