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

    Neuronpedia

    INDEX
    Explanations

    danger

    np_max-act · gemini-2.0-flash

    This neuron flags references to dangerous natural threats or hazards (e.g. wild or prehistoric animals, asteroids).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     offic
    -0.06
     referencia
    -0.06
    ��
    -0.06
    ycler
    -0.06
     poc
    -0.06
    (rotation
    -0.06
    状
    -0.06
     syndrome
    -0.06
     Anne
    -0.06
    ycling
    -0.06
    POSITIVE LOGITS
     ALTER
    0.06
    数
    0.06
    ‐‐
    0.06
     Late
    0.06
     inoc
    0.06
    =./
    0.06
     adversary
    0.06
    _GATE
    0.06
    .setStyle
    0.06
     Âu
    0.06
    Act Density 0.045%

    No Known Activations