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

    Neuronpedia

    INDEX
    Explanations

    Code/URLs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    搓
    -0.07
     Arab
    -0.07
     struggle
    -0.06
    嘣
    -0.06
    将士
    -0.06
     unavoidable
    -0.06
     bone
    -0.06
    ما
    -0.06
     commend
    -0.06
    למו
    -0.06
    POSITIVE LOGITS
     '/',
    0.08
     максималь
    0.08
    Phase
    0.08
     declar
    0.08
     [/
    0.08
    .MULT
    0.07
     supern
    0.07
    "She
    0.07
    alık
    0.07
     expres
    0.07
    Act Density 0.038%

    No Known Activations