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

    Neuronpedia

    INDEX
    Explanations

    multiple

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Strikes
    -0.07
     VIEW
    -0.07
     流
    -0.07
     Sicher
    -0.07
     beyaz
    -0.06
     loin
    -0.06
     بار
    -0.06
    RTL
    -0.06
    	diff
    -0.06
    İL
    -0.06
    POSITIVE LOGITS
    .ld
    0.07
    acles
    0.07
    ianne
    0.07
    .onOptionsItemSelected
    0.06
     invented
    0.06
    ۱۹۶
    0.06
    맨
    0.06
    .Id
    0.06
    },{
    0.06
     />";↵
    0.06
    Act Density 0.046%

    No Known Activations