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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    BASE
    -0.07
    (destination
    -0.07
     máu
    -0.07
     kaç
    -0.06
    .seconds
    -0.06
    THREAD
    -0.06
    وسط
    -0.06
     obyvatel
    -0.06
     skulls
    -0.06
     اين
    -0.06
    POSITIVE LOGITS
     bracket
    0.06
     دیگری
    0.06
    wrapper
    0.06
     düzenlem
    0.06
     enhances
    0.06
    ального
    0.06
    quipe
    0.06
     см
    0.06
    clause
    0.06
     Brother
    0.06
    Act Density 0.132%

    No Known Activations