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

    Neuronpedia

    INDEX
    Explanations

    bypassing security

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     velmi
    -0.07
    Ny
    -0.06
    656
    -0.06
    _Group
    -0.06
    fieldset
    -0.06
     SIMD
    -0.06
    addAction
    -0.06
    .NoArgsConstructor
    -0.06
     depicts
    -0.06
    .latitude
    -0.06
    POSITIVE LOGITS
    -speed
    0.07
     duly
    0.06
    خان
    0.06
    خر
    0.06
     України
    0.06
     выбор
    0.06
     certainly
    0.06
    낸
    0.06
     wm
    0.06
    	BYTE
    0.06
    Act Density 0.023%

    No Known Activations