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

    Neuronpedia

    INDEX
    Explanations

    loop indices

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    encrypt
    -0.08
     Backend
    -0.06
    (()
    -0.06
     ситуа
    -0.06
    _FAST
    -0.06
    @admin
    -0.06
    .present
    -0.06
     shields
    -0.06
     whether
    -0.06
    (Method
    -0.06
    POSITIVE LOGITS
     bryster
    0.07
    ้ม
    0.06
    营
    0.06
     関
    0.06
     fall
    0.06
     Seoul
    0.06
     chu
    0.06
     searchString
    0.06
     Bert
    0.06
    achusetts
    0.06
    Act Density 0.006%

    No Known Activations