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

    Neuronpedia

    INDEX
    Explanations

    range, decisions, macOS, string prefix

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     پور
    0.38
    ियार
    0.38
     چهار
    0.37
    кове
    0.37
     Glast
    0.37
     Rex
    0.36
     iner
    0.36
    लाल
    0.35
     Nazar
    0.35
     Aire
    0.35
    POSITIVE LOGITS
     mote
    0.38
     ք
    0.38
    राधना
    0.37
    stic
    0.37
    ród
    0.37
    庠
    0.37
    オプション
    0.36
    AVY
    0.36
     antes
    0.36
    vod
    0.35
    Act Density 0.046%

    No Known Activations