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

    Neuronpedia

    INDEX
    Explanations

    implementing code and software

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    تيجة
    0.38
    irties
    0.36
    sville
    0.36
    ెక్
    0.36
     Bartlett
    0.35
    𝔦
    0.35
     কুট
    0.34
     Baldwin
    0.34
    𝖎
    0.33
    กระ
    0.33
    POSITIVE LOGITS
     অক্ষর
    0.44
     Norm
    0.42
     Letter
    0.40
    cal
    0.40
     Mesh
    0.40
    afil
    0.40
     پزش
    0.39
    avanja
    0.39
    不够
    0.39
     lettres
    0.38
    Act Density 0.000%

    No Known Activations