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

    Neuronpedia

    INDEX
    Explanations

    data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     тран
    -0.08
    ipe
    -0.07
     stall
    -0.07
    	TR
    -0.07
    انيا
    -0.07
     BET
    -0.07
     önce
    -0.06
    .Flow
    -0.06
    황
    -0.06
     เง
    -0.06
    POSITIVE LOGITS
    Kernel
    0.07
    Eat
    0.06
     Repair
    0.06
    ��
    0.06
     Published
    0.06
    ů
    0.06
     moistur
    0.06
    LANGADM
    0.06
    ��
    0.06
    stay
    0.06
    Act Density 0.012%

    No Known Activations