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

    Neuronpedia

    INDEX
    Explanations

    latex environments and equations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     डिस्कस
    0.42
    嬙
    0.41
    CreateWall
    0.40
    ÁN
    0.38
    ಪ್ಪು
    0.38
    蜢
    0.37
    sklär
    0.37
     იყოს
    0.37
    מן
    0.36
    膯
    0.36
    POSITIVE LOGITS
     environment
    0.41
     ambiente
    0.36
     dotenv
    0.35
     ambiental
    0.35
     ass
    0.35
     star
    0.35
     Hav
    0.35
     ist
    0.34
     Hic
    0.34
    nave
    0.33
    Act Density 0.000%

    No Known Activations