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

    Neuronpedia

    INDEX
    Explanations

    technical terms

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     অঙ্ক
    0.57
    ସ୍
    0.55
     कपड़े
    0.54
    𝑧
    0.54
    érios
    0.53
     громадян
    0.53
     brahm
    0.52
    𝐺
    0.52
     трубы
    0.52
    颏
    0.52
    POSITIVE LOGITS
     Flux
    0.63
    Flux
    0.59
     Bits
    0.59
    傛
    0.57
     investigative
    0.57
     PN
    0.55
     respecter
    0.55
     tester
    0.54
     TFT
    0.54
     abi
    0.53
    Act Density 0.001%

    No Known Activations