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

    Neuronpedia

    INDEX
    Explanations

    bridge

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .uniform
    -0.07
    /";↵↵
    -0.07
    ogs
    -0.07
    iled
    -0.07
     Harper
    -0.07
     를
    -0.07
    goals
    -0.06
    ());
↵
    -0.06
     مالی
    -0.06
     mornings
    -0.06
    POSITIVE LOGITS
     fantast
    0.06
     candidacy
    0.06
    Regards
    0.06
    ▲
    0.06
    ","",
    0.06
     SHARE
    0.06
    retry
    0.06
    _STATE
    0.06
     questi
    0.06
     správ
    0.06
    Act Density 0.202%

    No Known Activations