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

    Neuronpedia

    INDEX
    Explanations

    /home

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     resistor
    -0.07
    erte
    -0.07
     раз
    -0.07
    ящ
    -0.07
     nebylo
    -0.06
     نو
    -0.06
    Vertex
    -0.06
    olen
    -0.06
    باشد
    -0.06
     인증
    -0.06
    POSITIVE LOGITS
    /home
    0.07
     روسیه
    0.07
     COVID
    0.06
     |:
    0.06
     WWII
    0.06
    192
    0.06
     Asked
    0.06
    189
    0.06
     ngoài
    0.06
    559
    0.06
    Act Density 0.000%

    No Known Activations