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

    Neuronpedia

    INDEX
    Explanations

    computer code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    recogn
    -0.07
     planets
    -0.07
     yourself
    -0.06
     Dropout
    -0.06
    ≤
    -0.06
    stores
    -0.06
     declines
    -0.06
     occupations
    -0.06
    .aspect
    -0.06
     theat
    -0.06
    POSITIVE LOGITS
    .userService
    0.07
    	file
    0.07
     Tun
    0.07
     TAR
    0.06
     toys
    0.06
     Buffered
    0.06
    証
    0.06
     Tet
    0.06
     MED
    0.06
     انسان
    0.06
    Act Density 0.039%

    No Known Activations