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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on tokens in statements reporting the current date and time.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    	th
    -0.06
    ayacak
    -0.06
    らく
    -0.06
    adu
    -0.06
    „P
    -0.06
    ену
    -0.06
    쓰
    -0.06
    ैद
    -0.06
    rh
    -0.05
    }).
    -0.05
    POSITIVE LOGITS
     Brick
    0.07
     Listener
    0.07
    //----------------------------------------------------------------------------
    0.07
     lửa
    0.07
     knit
    0.06
    circ
    0.06
     linux
    0.06
     anatomy
    0.06
     nuisance
    0.06
    american
    0.06
    Act Density 0.005%

    No Known Activations