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

    Neuronpedia

    INDEX
    Explanations

    scientific studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [keys
    -0.06
     год
    -0.06
     joints
    -0.06
     gate
    -0.06
     якості
    -0.06
    -entry
    -0.06
    =u
    -0.06
    thumb
    -0.06
    /my
    -0.06
     gele
    -0.06
    POSITIVE LOGITS
    -custom
    0.06
    .ss
    0.06
     lil
    0.06
    ên
    0.06
     getSession
    0.06
    UniqueId
    0.06
    CoreApplication
    0.06
    sburg
    0.06
     bloss
    0.06
    rawtypes
    0.06
    Act Density 0.008%

    No Known Activations