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

    Neuronpedia

    INDEX
    Explanations

    my response

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     кома
    0.41
    عب
    0.40
    FFIC
    0.39
     officials
    0.39
    )?
    0.38
     corte
    0.37
    Leb
    0.37
     अधिकारियों
    0.37
    Henderson
    0.37
    Moh
    0.36
    POSITIVE LOGITS
     scalar
    0.49
     múlti
    0.49
     Riemannian
    0.47
     favicon
    0.47
     controller
    0.46
     gamepad
    0.45
     Namespace
    0.44
     Semantic
    0.44
     Controller
    0.44
    语义
    0.43
    Act Density 0.001%

    No Known Activations