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

    Neuronpedia

    INDEX
    Explanations

    C header definitions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     male
    -0.08
     अज
    -0.07
     ara
    -0.07
     collectors
    -0.07
     ilan
    -0.06
     chicken
    -0.06
    era
    -0.06
    ]',↵
    -0.06
     Ancak
    -0.06
    -positive
    -0.06
    POSITIVE LOGITS
    (func
    0.07
     proport
    0.06
     comments
    0.06
     Palestinian
    0.06
    vertiser
    0.06
    Inspectable
    0.06
     çözüm
    0.06
    ING
    0.06
    pción
    0.06
     boarding
    0.06
    Act Density 0.005%

    No Known Activations