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

    Neuronpedia

    INDEX
    Explanations

    code, programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    防治
    -0.07
     PRO
    -0.07
    消防
    -0.07
    clare
    -0.07
     warning
    -0.07
    不容
    -0.07
     pre
    -0.07
    防范
    -0.07
     prim
    -0.07
    pre
    -0.06
    POSITIVE LOGITS
     sharedApplication
    0.08
     fwd
    0.08
     retail
    0.07
    を行い
    0.07
    帶來
    0.07
    干活
    0.07
     şik
    0.07
     mats
    0.07
     Decay
    0.07
    )];
↵
    0.07
    Act Density 0.101%

    No Known Activations