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

    Neuronpedia

    INDEX
    Explanations

    No

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .ht
    -0.07
    -validator
    -0.07
     complications
    -0.06
    .si
    -0.06
    (sent
    -0.06
    محمد
    -0.06
    ENDIF
    -0.06
    ]").
    -0.06
     北
    -0.06
    وط
    -0.06
    POSITIVE LOGITS
     hyster
    0.06
     أح
    0.06
    We
    0.06
     Query
    0.06
     hue
    0.06
    783
    0.06
    arranty
    0.06
     exercises
    0.06
     lượng
    0.06
    placement
    0.06
    Act Density 0.005%

    No Known Activations