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

    Neuronpedia

    INDEX
    Explanations

    theory

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     radi
    -0.07
     질
    -0.06
    ...";↵
    -0.06
    XYZ
    -0.06
    ….↵↵
    -0.06
    	offset
    -0.06
     "-";↵
    -0.06
    Leod
    -0.06
    ęż
    -0.06
     Austrian
    -0.06
    POSITIVE LOGITS
     blas
    0.07
    ederland
    0.06
     dared
    0.06
    �
    0.06
    spd
    0.06
     Cumhuriyeti
    0.06
     disciplines
    0.06
    ≠
    0.06
     searchData
    0.06
     Likely
    0.06
    Act Density 0.027%

    No Known Activations