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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     W
    -0.07
    Dims
    -0.06
    -low
    -0.06
     rede
    -0.06
     bedside
    -0.06
     влади
    -0.06
     pela
    -0.06
     exemp
    -0.06
    (Job
    -0.06
    ologie
    -0.06
    POSITIVE LOGITS
    �
    0.07
     uvol
    0.07
     STDOUT
    0.06
     plural
    0.06
     partic
    0.06
    !=-
    0.06
    AUSE
    0.06
    ustr
    0.06
     �
    0.06
    astic
    0.06
    Act Density 0.005%

    No Known Activations