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

    Neuronpedia

    INDEX
    Explanations

    cancellation

    np_max-act · gemini-2.0-flash

    The neuron flags mentions of withdrawing or retracting actions (e.g. “withdrew,” “withdrawing,” “off”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     вопрос
    -0.07
    ียน
    -0.06
    _CHAN
    -0.06
    _MATCH
    -0.06
    ��
    -0.06
    PropertyDescriptor
    -0.06
    คร
    -0.06
     competitiveness
    -0.06
    Õ
    -0.06
    Trust
    -0.06
    POSITIVE LOGITS
    овала
    0.07
    185
    0.07
     withdrawn
    0.07
    �
    0.07
     �
    0.07
     grands
    0.07
     αυτό
    0.06
     fres
    0.06
     pleased
    0.06
     Sınıf
    0.06
    Act Density 0.018%

    No Known Activations