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

    Neuronpedia

    INDEX
    Explanations

    Computer hardware specifications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     crash
    -0.08
     crashes
    -0.07
     शक्त
    -0.07
    确定
    -0.07
    (cr
    -0.07
    执行
    -0.07
     अंग
    -0.07
     basically
    -0.07
     effective
    -0.07
    ounding
    -0.07
    POSITIVE LOGITS
    Electrical
    0.09
     Cous
    0.08
     erot
    0.08
     keskust
    0.08
     bescherm
    0.08
    .placeholder
    0.08
     hygiene
    0.08
     Electrical
    0.08
     protège
    0.08
     hygien
    0.08
    Act Density 0.001%

    No Known Activations