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

    Neuronpedia

    INDEX
    Explanations

    Network intrusion detection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stagger
    -0.09
     counties
    -0.08
    ಾರಿಗೆ
    -0.07
     medial
    -0.07
     cleared
    -0.07
     nicely
    -0.07
     kostet
    -0.07
    mv
    -0.07
    .len
    -0.07
    mise
    -0.07
    POSITIVE LOGITS
     adulter
    0.09
     النظام
    0.09
     Arro
    0.09
     gült
    0.08
     Patterns
    0.08
    �
    0.08
     પેટ
    0.08
     unhealthy
    0.08
     abnormal
    0.08
     වැ
    0.08
    Act Density 0.010%

    No Known Activations