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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _CAPACITY
    -0.07
     bodies
    -0.07
     Hwy
    -0.07
     جمهوری
    -0.06
    .acc
    -0.06
    ालय
    -0.06
     stuck
    -0.06
    (tile
    -0.06
     valleys
    -0.06
    .output
    -0.06
    POSITIVE LOGITS
    ่อส
    0.08
     repertoire
    0.07
     th
    0.07
     cham
    0.06
    	If
    0.06
     період
    0.06
    √
    0.06
    lášení
    0.06
    -register
    0.06
    Vy
    0.06
    Act Density 0.012%

    No Known Activations