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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ãy
    -0.06
     KeyCode
    -0.06
     stone
    -0.06
    "a
    -0.06
     jste
    -0.06
     Broken
    -0.06
    LETED
    -0.06
    such
    -0.06
     translation
    -0.05
    bias
    -0.05
    POSITIVE LOGITS
     family
    0.09
     Family
    0.08
    family
    0.08
    .number
    0.07
     FAMILY
    0.07
    운
    0.07
    арат
    0.07
    (Get
    0.07
    Ptr
    0.07
    .family
    0.07
    Act Density 0.007%

    No Known Activations