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

    Neuronpedia

    INDEX
    Explanations

    hyphen

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     assemble
    -0.08
    (Container
    -0.08
    /SP
    -0.07
    ?id
    -0.07
     asse
    -0.07
    <?>
    -0.07
    -0.07
    .Container
    -0.07
    ?a
    -0.07
    aliases
    -0.07
    POSITIVE LOGITS
    lemm
    0.08
     clín
    0.07
     민
    0.07
     команды
    0.07
     dota
    0.07
    лок
    0.07
    调
    0.07
     domine
    0.07
     flatter
    0.07
    Zh
    0.07
    Act Density 0.024%
    No Known Activations