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

    Neuronpedia

    INDEX
    Explanations

    we

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     politely
    -0.07
     departure
    -0.06
    घ
    -0.06
     severity
    -0.06
     hashed
    -0.06
    aea
    -0.06
     شوند
    -0.06
    aida
    -0.06
    .dk
    -0.06
     Lamb
    -0.06
    POSITIVE LOGITS
     SPDX
    0.07
    fm
    0.07
     Slider
    0.07
    due
    0.06
     saldır
    0.06
     PROFILE
    0.06
    .tensor
    0.06
    잡담
    0.06
    (fc
    0.06
    (Field
    0.06
    Act Density 0.000%

    No Known Activations