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

    Neuronpedia

    INDEX
    Explanations

    layers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    juana
    -0.07
    .EventHandler
    -0.07
     흔
    -0.06
     SEARCH
    -0.06
    _ro
    -0.06
     tofu
    -0.06
    232
    -0.06
    enery
    -0.06
    iens
    -0.06
    .distance
    -0.06
    POSITIVE LOGITS
     tỉ
    0.06
     clearer
    0.06
     inferior
    0.06
    ETS
    0.06
    0.06
     meals
    0.06
    FUNC
    0.06
    LOUR
    0.06
     sides
    0.06
     concerning
    0.06
    Act Density 0.005%

    No Known Activations