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

    Neuronpedia

    INDEX
    Explanations

    virtual environment activation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    O
    0.75
    PY
    0.74
    s
    0.69
     。
    0.68
    Ant
    0.67
    D
    0.66
    ओ
    0.66
    K
    0.65
    M
    0.64
    traces
    0.64
    POSITIVE LOGITS
     값
    0.84
     گھر
    0.83
     ძალიან
    0.79
     Surname
    0.79
    嵬
    0.79
     Saheb
    0.79
    তা
    0.79
     Perception
    0.79
     haystack
    0.78
     Vielen
    0.78
    Act Density 0.001%

    No Known Activations