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

    Neuronpedia

    INDEX
    Explanations

    -free

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    姐
    -0.07
    贷
    -0.07
    啥
    -0.07
    工信
    -0.07
     subsystem
    -0.07
    xca
    -0.06
     jo
    -0.06
    💢
    -0.06
    heartbeat
    -0.06
    POSITIVE LOGITS
    Throw
    0.08
    _twitter
    0.07
    andscape
    0.07
    "]))
    0.07
    -Headers
    0.07
    berra
    0.06
    两三
    0.06
    reveal
    0.06
     guessed
    0.06
     Pressure
    0.06
    Act Density 0.001%

    No Known Activations