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

    Neuronpedia

    INDEX
    Explanations

    code examples

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    CLU
    -0.06
    ค
    -0.06
    Pe
    -0.06
    Identity
    -0.06
     swiftly
    -0.06
    τής
    -0.05
     Tenn
    -0.05
    -talk
    -0.05
     fists
    -0.05
     Dart
    -0.05
    POSITIVE LOGITS
    	glog
    0.07
    має
    0.07
    =j
    0.07
     Urg
    0.07
    =row
    0.07
    ">&#
    0.07
     �
    0.07
     onSubmit
    0.06
    ��
    0.06
    =min
    0.06
    Act Density 0.048%

    No Known Activations