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

    Neuronpedia

    INDEX
    Explanations

    C/C++ include directives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     трудно
    1.05
    ето
    1.02
     ee
    0.94
     cleaned
    0.93
     deltaTime
    0.92
     embodiments
    0.92
     muscles
    0.91
     potencialmente
    0.91
     termites
    0.91
     adherents
    0.91
    POSITIVE LOGITS
    део
    1.01
    福利
    0.99
    a
    0.99
    woorden
    0.98
    tos
    0.96
    smallskip
    0.94
    備
    0.93
    ല
    0.92
    मुक्त
    0.92
    許
    0.92
    Act Density 0.004%

    No Known Activations