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

    Neuronpedia

    INDEX
    Explanations

    Scientific/Technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ्बर
    -0.07
     �
    -0.06
     بول
    -0.06
     Movie
    -0.06
     trực
    -0.06
     Stap
    -0.06
     judging
    -0.06
     longstanding
    -0.06
     Sebastian
    -0.06
     exercises
    -0.06
    POSITIVE LOGITS
     中国
    0.07
     handleMessage
    0.06
    سية
    0.06
     SERVER
    0.06
    -display
    0.06
    .Imp
    0.06
    уп
    0.06
    ounded
    0.06
     Opr
    0.06
    frau
    0.06
    Act Density 0.125%

    No Known Activations