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

    Neuronpedia

    INDEX
    Explanations

    shrinks repeatedly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     сал
    0.55
    jarah
    0.46
     पकड़ा
    0.45
    舧
    0.44
    পাড়া
    0.44
     fath
    0.44
     euismod
    0.43
     بنائیں
    0.43
     นิด
    0.43
    രക്ഷ
    0.42
    POSITIVE LOGITS
     '/
    0.52
     INFIN
    0.48
     Aliment
    0.46
    तरी
    0.45
     INFO
    0.44
    ujemo
    0.43
     '__
    0.43
     Frame
    0.43
     Astrophysics
    0.42
    components
    0.42
    Act Density 0.000%

    No Known Activations