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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	request
    -0.07
    [element
    -0.07
     تخصص
    -0.06
    orts
    -0.06
     آزمایش
    -0.06
    ترین
    -0.06
    agar
    -0.06
    ektör
    -0.06
    .Gradient
    -0.06
    .Op
    -0.06
    POSITIVE LOGITS
    ���
    0.07
    -Jul
    0.07
     inh
    0.06
     qualities
    0.06
     Mari
    0.06
    062
    0.06
     Zelda
    0.06
     drilled
    0.06
     CreateUser
    0.06
    _training
    0.06
    Act Density 0.104%

    No Known Activations