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

    Neuronpedia

    INDEX
    Explanations

    season generously

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    缺失
    0.33
     linearly
    0.33
     chroma
    0.33
     лаь
    0.32
     ámbitos
    0.31
     ambi
    0.31
     increments
    0.31
     dared
    0.31
     suffice
    0.31
     increment
    0.30
    POSITIVE LOGITS
    Another
    0.43
    Think
    0.39
    One
    0.38
    Sh
    0.38
    Firstly
    0.38
    Secondly
    0.37
    Many
    0.36
    Plan
    0.36
    Organ
    0.35
    Bluetooth
    0.35
    Act Density 0.000%

    No Known Activations