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

    Neuronpedia

    INDEX
    Explanations

    4

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .isDebugEnabled
    -0.07
    ([-
    -0.07
    .gridx
    -0.07
    硿
    -0.07
     توف
    -0.07
    $stmt
    -0.07
     он
    -0.07
    .hostname
    -0.07
    潸
    -0.06
    哽
    -0.06
    POSITIVE LOGITS
    WN
    0.08
     MY
    0.07
    МА
    0.07
     dẫn
    0.07
    construction
    0.06
     continental
    0.06
     trajectory
    0.06
     neural
    0.06
    DA
    0.06
    Human
    0.06
    Act Density 0.001%

    No Known Activations