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

    Neuronpedia

    INDEX
    Explanations

    technical writing

    np_max-act · gemini-2.0-flash

    This neuron activates on hyphenated compound words (or compound modifiers joined by hyphens).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     данны
    -0.07
     gx
    -0.07
     pole
    -0.07
    ульта
    -0.07
    -sk
    -0.06
    linux
    -0.06
     unlocked
    -0.06
     gỗ
    -0.06
    /java
    -0.06
    	cursor
    -0.06
    POSITIVE LOGITS
    _contact
    0.07
     şöyle
    0.06
    ultiply
    0.06
    =this
    0.06
    面的
    0.06
    _CONNECTION
    0.06
    	errors
    0.06
    >`;↵
    0.06
    _prot
    0.05
     outlier
    0.05
    Act Density 0.632%

    No Known Activations