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

    Neuronpedia

    INDEX
    Explanations

    Work

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     speech
    -0.06
    릴
    -0.06
    ース
    -0.06
     用户
    -0.06
    님의
    -0.06
    、お
    -0.06
    Philip
    -0.06
     Princip
    -0.06
    �
    -0.06
     urgently
    -0.06
    POSITIVE LOGITS
     Killing
    0.07
    (Program
    0.06
    _EXPORT
    0.06
     pave
    0.06
     Wak
    0.06
     toss
    0.06
    _Real
    0.06
     Photo
    0.06
    htags
    0.06
     Potion
    0.06
    Act Density 0.042%

    No Known Activations