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

    Neuronpedia

    INDEX
    Explanations

    horizontal lines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    HERS
    0.38
     scol
    0.38
    ارا
    0.37
    intens
    0.37
     RL
    0.37
    RAP
    0.37
    Rg
    0.37
     RAP
    0.37
    ][-
    0.37
     Rg
    0.37
    POSITIVE LOGITS
     Shiraz
    0.41
     Shir
    0.41
     Hort
    0.40
     Holman
    0.39
    üyük
    0.38
     Clerk
    0.38
    ̘
    0.38
    雯
    0.37
    ंकि
    0.36
     Fres
    0.36
    Act Density 0.002%

    No Known Activations