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

    Neuronpedia

    INDEX
    Explanations

    code, data, programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /title
    -0.08
     Det
    -0.07
     Normal
    -0.07
     záv
    -0.07
     přísluš
    -0.06
    rå
    -0.06
    Direct
    -0.06
    شة
    -0.06
     rejected
    -0.06
    hc
    -0.06
    POSITIVE LOGITS
     Usuarios
    0.06
    opcode
    0.06
    Carlos
    0.06
    napshot
    0.06
     dp
    0.06
     ^=
    0.06
    52
    0.06
     transport
    0.06
     Scalars
    0.05
    	typedef
    0.05
    Act Density 0.002%

    No Known Activations