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

    Neuronpedia

    INDEX
    Explanations

    compliance

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _BASE
    -0.07
     Free
    -0.07
    ystack
    -0.07
    oston
    -0.07
    也是很
    -0.07
    ----------------------------
    -0.07
    summer
    -0.07
    ✦
    -0.07
    raphic
    -0.07
    那天
    -0.06
    POSITIVE LOGITS
    /F
    0.07
    _context
    0.07
    (exp
    0.07
    뽐
    0.07
     activations
    0.07
     П
    0.06
    andExpect
    0.06
     prio
    0.06
    搦
    0.06
    Font
    0.06
    Act Density 0.011%

    No Known Activations