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

    Neuronpedia

    INDEX
    Explanations

    code or programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cynthia
    -0.07
     سایر
    -0.06
     hiring
    -0.06
     cured
    -0.06
    静
    -0.06
    critical
    -0.06
     villains
    -0.06
     question
    -0.06
    Changing
    -0.06
    disable
    -0.06
    POSITIVE LOGITS
    تك
    0.07
     �
    0.07
    -|
    0.06
     جي
    0.06
     Düz
    0.06
    wj
    0.06
    °
    0.06
     já
    0.06
    $mail
    0.06
    amentos
    0.06
    Act Density 0.147%

    No Known Activations