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

    Neuronpedia

    INDEX
    Explanations

    Exploit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wed
    -0.08
    IENTATION
    -0.07
     Gent
    -0.07
     various
    -0.07
    _indx
    -0.07
     governmental
    -0.07
     pronunciation
    -0.06
    rz
    -0.06
     emergency
    -0.06
    /remove
    -0.06
    POSITIVE LOGITS
     exploiting
    0.10
     exploited
    0.10
     exploit
    0.10
     exploitation
    0.09
     explo
    0.09
     exploits
    0.07
    探
    0.07
     облад
    0.07
     Produkt
    0.07
    fait
    0.07
    Act Density 0.006%

    No Known Activations