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

    Neuronpedia

    INDEX
    Explanations

    animals

    np_max-act · gemini-2.0-flash

    This neuron detects common multiword animal species names (e.g. “horseshoe bat,” “fruit fly,” “knob‐billed fruit dove,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     analog
    -0.07
     Ran
    -0.06
    idepress
    -0.06
    Insets
    -0.06
    irmware
    -0.06
     impass
    -0.06
     Relief
    -0.06
     bản
    -0.06
     White
    -0.06
     Bow
    -0.05
    POSITIVE LOGITS
    	make
    0.07
     drei
    0.07
    }/
    0.07
     čím
    0.07
    [:
    0.07
     Cooking
    0.06
    ／
    0.06
    (_('
    0.06
    や
    0.06
     '('
    0.06
    Act Density 0.018%

    No Known Activations