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

    Neuronpedia

    INDEX
    Explanations

    x

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Page
    -0.08
     CNS
    -0.07
     Bernie
    -0.07
     species
    -0.07
     memb
    -0.07
     חיובי
    -0.07
    _batches
    -0.07
     organizations
    -0.06
     Somerset
    -0.06
    ��
    -0.06
    POSITIVE LOGITS
    �
    0.07
    적이
    0.07
    (callback
    0.07
    壓
    0.07
    lib
    0.07
    納
    0.07
     qualifications
    0.06
    乳
    0.06
    	callback
    0.06
     Notification
    0.06
    Act Density 0.177%

    No Known Activations