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

    Neuronpedia

    INDEX
    Explanations

    Technical articles/discussions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     οποίο
    -0.07
     보면
    -0.06
    陵
    -0.06
     Amelia
    -0.06
    (sim
    -0.06
     Rings
    -0.06
    lings
    -0.06
    系列
    -0.06
     magnitude
    -0.06
     Maj
    -0.06
    POSITIVE LOGITS
    expression
    0.07
     стари
    0.06
    DBus
    0.06
     MonoBehaviour
    0.06
     HttpRequest
    0.06
    ?"↵↵
    0.06
     assaulted
    0.06
    ression
    0.06
    trust
    0.06
    ário
    0.06
    Act Density 0.000%

    No Known Activations