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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ý
    -0.07
    .objects
    -0.07
    (row
    -0.07
    67
    -0.07
     assurance
    -0.06
    (Role
    -0.06
    _Item
    -0.06
    107
    -0.06
     `{
    -0.06
    72
    -0.06
    POSITIVE LOGITS
    ────
    0.07
     strm
    0.07
     //--
    0.06
     Đào
    0.06
     aktu
    0.06
     identical
    0.06
     расч
    0.06
    ichage
    0.06
     방법
    0.06
     développement
    0.06
    Act Density 0.435%

    No Known Activations