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

    Neuronpedia

    INDEX
    Explanations

    aligned

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Phân
    -0.06
    validators
    -0.06
     basal
    -0.06
    |$
    -0.06
     educ
    -0.06
     deeper
    -0.06
     ipairs
    -0.06
    .Line
    -0.06
    MV
    -0.05
    ________________________________________________________________
    -0.05
    POSITIVE LOGITS
     mluv
    0.07
     worked
    0.07
    etag
    0.07
    ,state
    0.07
     součást
    0.07
     حد
    0.06
    LOAT
    0.06
    hrad
    0.06
    ="#"><
    0.06
    otions
    0.06
    Act Density 0.002%

    No Known Activations