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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    院子
    -0.08
    ştırma
    -0.07
    ilen
    -0.07
    _simulation
    -0.07
    🦙
    -0.07
    /X
    -0.07
    �
    -0.07
     (;;)
    -0.07
     Fou
    -0.07
     FD
    -0.07
    POSITIVE LOGITS
    债券
    0.07
    盗
    0.07
    铜
    0.07
     ε
    0.07
    Reviewed
    0.07
     SW
    0.07
     Pets
    0.07
     tend
    0.06
    경
    0.06
     Friend
    0.06
    Act Density 0.000%

    No Known Activations