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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Insn
    -0.07
    嶂
    -0.07
     Volvo
    -0.07
    .ZERO
    -0.07
    .Unity
    -0.07
     Matters
    -0.07
     IoT
    -0.07
     mare
    -0.07
     uncert
    -0.07
    /entity
    -0.07
    POSITIVE LOGITS
    //↵
    0.08
    //
↵
    0.08
     podemos
    0.07
     فإن
    0.07
    **/↵
    0.07
    调节
    0.07
     ;
↵
    0.07
    ფ
    0.07
    ",
↵
    0.07
                    
↵
    0.07
    Act Density 0.002%

    No Known Activations