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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    \Object
    -0.06
    δες
    -0.06
     جور
    -0.06
    Exp
    -0.06
     manufactured
    -0.06
     Laf
    -0.06
     유저
    -0.06
     brutally
    -0.06
     클래스
    -0.06
     sucker
    -0.06
    POSITIVE LOGITS
     Digest
    0.07
     �
    0.06
     문
    0.06
     PIC
    0.06
    .Post
    0.06
     Assass
    0.06
     Anast
    0.06
    _fore
    0.06
    ]->
    0.06
    AUSE
    0.06
    Act Density 0.012%

    No Known Activations