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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    یری
    -0.07
     Even
    -0.07
     dean
    -0.07
     hostile
    -0.07
     microscopic
    -0.06
    _desc
    -0.06
    -bo
    -0.06
    ी
    -0.06
    horia
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    aturas
    0.08
     usar
    0.07
     aggress
    0.06
     Valencia
    0.06
     calculator
    0.06
    -sama
    0.06
     Solid
    0.06
    IR
    0.06
     [=
    0.06
    327
    0.06
    Act Density 0.009%

    No Known Activations