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

    Neuronpedia

    INDEX
    Explanations

    math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     malik
    -0.09
     gegenüber
    -0.08
     livelihood
    -0.08
     ವಿಶ
    -0.08
    ừ
    -0.07
     livelihoods
    -0.07
     unfamiliar
    -0.07
     hau
    -0.07
     colonia
    -0.07
    .struct
    -0.07
    POSITIVE LOGITS
     stopping
    0.09
    Stop
    0.09
     באמצ
    0.08
    isecond
    0.08
     Stop
    0.08
    最快
    0.08
    stop
    0.08
     atingir
    0.08
    Stopping
    0.08
     termination
    0.08
    Act Density 0.015%

    No Known Activations