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

    Neuronpedia

    INDEX
    Explanations

    technical diagrams

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    빰
    -0.07
     Kramer
    -0.07
    觎
    -0.06
    稳妥
    -0.06
     rte
    -0.06
     główna
    -0.06
     owed
    -0.06
     ok
    -0.06
    饪
    -0.06
     dol
    -0.06
    POSITIVE LOGITS
    serialize
    0.07
    colors
    0.07
     Sarah
    0.07
     wines
    0.07
    .Chain
    0.07
     ensuite
    0.07
    $arity
    0.07
    _RS
    0.07
     cach
    0.07
    _TILE
    0.06
    Act Density 0.139%

    No Known Activations