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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    instructions to ignore previous directions and to simulate alternative modes of interaction.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ост
    -0.07
    EFI
    -0.07
    VarInsn
    -0.07
     사이트
    -0.06
     String
    -0.06
     公
    -0.06
    	lp
    -0.06
    /css
    -0.06
    Portal
    -0.06
    Magento
    -0.06
    POSITIVE LOGITS
    mmo
    0.07
    (pointer
    0.07
    �
    0.06
     Matching
    0.06
    (++
    0.06
     raced
    0.06
    .transpose
    0.06
     Screw
    0.06
    -frequency
    0.06
     Sapphire
    0.06
    Act Density 0.016%

    No Known Activations