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

    Neuronpedia

    INDEX
    Explanations

    communication

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     During
    -0.07
     Puppet
    -0.07
     enlarge
    -0.06
     /=
    -0.06
     blind
    -0.06
    ww
    -0.06
    Noise
    -0.06
     University
    -0.06
    OUNCE
    -0.06
     nebezpeč
    -0.06
    POSITIVE LOGITS
     YYYY
    0.07
     sélection
    0.07
     SIGN
    0.06
     Holden
    0.06
    quia
    0.06
    .Power
    0.06
    swick
    0.06
    �
    0.06
     Squad
    0.06
    (argc
    0.06
    Act Density 0.172%

    No Known Activations