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

    Neuronpedia

    INDEX
    Explanations

    4

    np_max-act · gemini-2.0-flash

    The neuron responds to informal, personal‐experience–style text—especially first‐person anecdotes and conversational forum/blog comments.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    	canvas
    -0.07
     Overlay
    -0.07
     답
    -0.06
     Rever
    -0.06
     pulp
    -0.06
    >({↵
    -0.06
     """.
    -0.06
     �
    -0.06
    .numpy
    -0.06
    _decorator
    -0.06
    POSITIVE LOGITS
     defensively
    0.07
     стоимость
    0.06
     гар
    0.06
    Trap
    0.06
     achievable
    0.06
     langs
    0.06
    _checksum
    0.06
    CSV
    0.06
     брос
    0.06
     onlar
    0.06
    Act Density 0.185%

    No Known Activations