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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    the main thing this neuron does is find past-tense verbs.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ával
    -0.07
    Monitoring
    -0.06
     números
    -0.06
     قرارد
    -0.06
    Credits
    -0.06
    Makes
    -0.06
     необходим
    -0.06
     méně
    -0.06
     Jane
    -0.06
    تمر
    -0.06
    POSITIVE LOGITS
    reject
    0.06
    Flexible
    0.06
     )↵↵
    0.06
     силу
    0.06
    _compress
    0.06
     #↵↵
    0.06
     scri
    0.06
    	DD
    0.06
     �
    0.06
     disagree
    0.06
    Act Density 0.044%

    No Known Activations