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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    norm
    -0.07
    egers
    -0.07
     rog
    -0.07
     rau
    -0.06
     vote
    -0.06
     lodash
    -0.06
     sea
    -0.06
     conspir
    -0.06
    )findViewById
    -0.06
    rar
    -0.06
    POSITIVE LOGITS
    _WITH
    0.08
     yapmak
    0.08
     With
    0.08
     Collaboration
    0.07
     TH
    0.07
    _FETCH
    0.07
    TH
    0.07
    <Text
    0.07
     PROVIDED
    0.07
    ัฐ
    0.07
    Act Density 0.033%

    No Known Activations