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

    Neuronpedia

    INDEX
    Explanations

    Code/technical language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ernet
    -0.07
     kuvvet
    -0.06
    attr
    -0.06
     Got
    -0.06
     cca
    -0.06
     نیر
    -0.06
    ="'.$
    -0.06
    ck
    -0.06
     MF
    -0.06
     ilan
    -0.05
    POSITIVE LOGITS
    Des
    0.07
     Spurs
    0.07
    ์↵
    0.06
    dyž
    0.06
    ､↵
    0.06
     exploring
    0.06
     введ
    0.06
     }))↵
    0.06
    wargs
    0.06
    Formation
    0.06
    Act Density 0.000%

    No Known Activations