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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     мен
    -0.07
     diplomats
    -0.07
     specific
    -0.07
    .Identity
    -0.07
    redient
    -0.06
     فناوری
    -0.06
     acheter
    -0.06
    (acc
    -0.06
    .currentUser
    -0.06
     nh
    -0.06
    POSITIVE LOGITS
    력이
    0.07
     Need
    0.06
    _unused
    0.06
     minion
    0.06
    เขต
    0.06
    voice
    0.06
     Peripheral
    0.06
    вит
    0.06
    Gender
    0.06
     Plain
    0.06
    Act Density 0.001%

    No Known Activations