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

    Neuronpedia

    INDEX
    Explanations

    file operations and references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fluid
    1.01
    িত্ব
    1.00
     loudest
    0.99
    الان
    0.96
     exacting
    0.96
     familiar
    0.95
     GDP
    0.93
     Valence
    0.93
    Rigidbody
    0.92
    ায়
    0.91
    POSITIVE LOGITS
    럿
    1.80
    :///
    1.72
    ipino
    1.57
     mignon
    1.40
    igree
    1.38
    omena
    1.37
     تعريف
    1.25
    夾
    1.24
    ://$
    1.21
     Apesar
    1.11
    Act Density 0.206%

    No Known Activations