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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     carro
    -0.07
    knowledge
    -0.07
    Os
    -0.06
     veterinary
    -0.06
    APT
    -0.06
    Speak
    -0.06
    Greater
    -0.06
    Accuracy
    -0.06
     maison
    -0.06
     meetings
    -0.06
    POSITIVE LOGITS
    acd
    0.07
    ‌ان
    0.07
    .dispose
    0.06
    occus
    0.06
     gồm
    0.06
    (UIAlertAction
    0.06
    vection
    0.06
    τηκε
    0.06
     clearInterval
    0.06
    ����
    0.06
    Act Density 0.021%

    No Known Activations