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

    Neuronpedia

    INDEX
    Explanations

    URLs and foreign language links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mRNAs
    0.30
     recomb
    0.29
     প্রথমেই
    0.29
     groupes
    0.28
    __:
    0.27
     penetrate
    0.27
     ያሉ
    0.27
     acceptors
    0.27
    患者
    0.27
    ’:
    0.27
    POSITIVE LOGITS
     и
    0.36
    पणे
    0.34
     teşekkür
    0.34
     übrigens
    0.34
     dito
    0.34
    ं
    0.34
     gimana
    0.33
    ore
    0.32
    google
    0.32
     और
    0.32
    Act Density 0.465%

    No Known Activations