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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    The neuron is looking for the word “introduction” (i.e. prompts asking for an introduction).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    	play
    -0.06
     slots
    -0.06
     appl
    -0.06
    Icon
    -0.06
     playful
    -0.06
    area
    -0.06
    čast
    -0.06
     WINDOWS
    -0.06
     pad
    -0.06
     gran
    -0.06
    POSITIVE LOGITS
     dateString
    0.07
     Liability
    0.07
     совсем
    0.06
     @{$
    0.06
    lerce
    0.06
     PERF
    0.06
     kah
    0.06
    _ADMIN
    0.06
    achable
    0.06
    /function
    0.06
    Act Density 0.004%

    No Known Activations