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

    Neuronpedia

    INDEX
    Explanations

    mathematical decompositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     مرة
    -0.07
    borne
    -0.07
    Coefficient
    -0.07
     im
    -0.06
    							
↵
    -0.06
    medium
    -0.06
    _gener
    -0.06
    stru
    -0.06
    posting
    -0.06
    .Ret
    -0.06
    POSITIVE LOGITS
    ife
    0.07
    色
    0.07
    ;$
    0.06
    _bs
    0.06
    _IS
    0.06
    odian
    0.06
    .RestController
    0.06
    τια
    0.06
    宾
    0.06
    िज
    0.06
    Act Density 0.062%

    No Known Activations