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

    Neuronpedia

    INDEX
    Explanations

    new

    np_max-act · gemini-2.0-flash

    This neuron doesn’t reliably pick up any content—its activations remain zero across all inputs. In other words, it never fires for any of these document parts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    vest
    -0.07
     semana
    -0.07
    upply
    -0.06
    Rand
    -0.06
    .put
    -0.06
     justification
    -0.06
     summer
    -0.06
    _EX
    -0.06
    頓
    -0.06
     ska
    -0.06
    POSITIVE LOGITS
    	LOGGER
    0.07
     negotiate
    0.07
     LeBron
    0.06
     rollback
    0.06
     reinstall
    0.06
    pizza
    0.06
     yeri
    0.06
     Nicolas
    0.06
    "]=="
    0.06
    _ACTIV
    0.06
    Act Density 0.012%

    No Known Activations