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

    Neuronpedia

    INDEX
    Explanations

    w

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    刀
    -0.07
    multiply
    -0.06
    .regex
    -0.06
    /us
    -0.06
     rice
    -0.06
    نة
    -0.06
     إلى
    -0.06
     malignant
    -0.06
    -Smith
    -0.06
    .reload
    -0.06
    POSITIVE LOGITS
     Thy
    0.07
    Observers
    0.07
     tím
    0.06
    NonNull
    0.06
    FAILURE
    0.06
    Mapped
    0.06
    éc
    0.06
     converted
    0.06
    �
    0.06
     brid
    0.06
    Act Density 0.002%

    No Known Activations