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

    Neuronpedia

    INDEX
    Explanations

    Community involvement

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Interactive
    -0.06
     installation
    -0.06
     riding
    -0.06
     hakk
    -0.06
     mounting
    -0.06
    athom
    -0.06
     joys
    -0.06
     Dave
    -0.06
     věd
    -0.06
     фин
    -0.06
    POSITIVE LOGITS
    atches
    0.07
     rank
    0.07
    .Fixed
    0.06
     належ
    0.06
    Attrib
    0.06
    enské
    0.06
    łu
    0.06
     OBS
    0.06
    unlikely
    0.06
    FINITE
    0.06
    Act Density 0.055%

    No Known Activations