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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Common
    -0.07
     Der
    -0.07
    前に
    -0.07
     suff
    -0.07
    reinterpret
    -0.06
    莨
    -0.06
     urn
    -0.06
     cabeza
    -0.06
    �
    -0.06
     ArrayBuffer
    -0.06
    POSITIVE LOGITS
    🇺
    0.07
    .localStorage
    0.07
     ainda
    0.07
    tm
    0.07
    Sq
    0.06
    𝘀
    0.06
    -color
    0.06
    浸泡
    0.06
     правило
    0.06
    ject
    0.06
    Act Density 0.001%

    No Known Activations