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

    Neuronpedia

    INDEX
    Explanations

    available to developers and researchers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ',
    0.39
     منسل
    0.39
     multiuser
    0.38
    чность
    0.38
     amenable
    0.38
    ')
    0.37
     откры
    0.36
     municip
    0.36
    stdin
    0.35
     मुं
    0.35
    POSITIVE LOGITS
     developers
    0.84
     Developers
    0.81
    Developers
    0.81
    developers
    0.71
    开发者
    0.68
     разработ
    0.66
     researchers
    0.63
     programmers
    0.62
     anyone
    0.61
     developer
    0.58
    Act Density 0.009%

    No Known Activations