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

    Neuronpedia

    INDEX
    Explanations

    32 16

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ymoon
    -0.07
     dishwasher
    -0.07
    _lb
    -0.07
    tl
    -0.07
    -camera
    -0.07
     republican
    -0.06
    노
    -0.06
     kilometers
    -0.06
    Toolbar
    -0.06
     Alvarez
    -0.06
    POSITIVE LOGITS
    ',$
    0.07
    .ObjectMapper
    0.06
    (separator
    0.06
    Une
    0.06
    Ada
    0.06
    ….
    0.06
     Uno
    0.06
     ********
    0.06
    рина
    0.05
     phê
    0.05
    Act Density 0.010%

    No Known Activations