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

    Neuronpedia

    INDEX
    Explanations

    Java service and component declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lyPlugin
    0.44
    addTarget
    0.43
    ⑷
    0.40
    CAG
    0.40
    លោក
    0.40
    롯
    0.40
     ሆ
    0.39
     Ljub
    0.39
    فيد
    0.39
    等が
    0.39
    POSITIVE LOGITS
    ère
    0.37
    gest
    0.37
     विस्तृत
    0.37
    neural
    0.37
    纭
    0.37
    hene
    0.36
    kil
    0.36
     fehl
    0.36
     fe
    0.35
     gewüns
    0.35
    Act Density 0.001%

    No Known Activations