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

    Neuronpedia

    INDEX
    Explanations

    WW

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rectangle
    -0.07
    (Pos
    -0.07
     string
    -0.06
     Hos
    -0.06
    .Floor
    -0.06
    .Product
    -0.06
    nothing
    -0.06
    .jetbrains
    -0.06
     itching
    -0.06
     panicked
    -0.06
    POSITIVE LOGITS
     lesbi
    0.07
    !<
    0.07
    [d
    0.07
     Влади
    0.07
    मत
    0.06
    =__
    0.06
    ív
    0.06
    。「
    0.06
    #__
    0.06
    ::|
    0.06
    Act Density 0.002%

    No Known Activations