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

    Neuronpedia

    INDEX
    Explanations

    protect

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Keys
    -0.07
     ABS
    -0.06
    _FRONT
    -0.06
     betray
    -0.06
    	mem
    -0.06
    藍
    -0.06
    (front
    -0.06
     Preservation
    -0.06
    -tested
    -0.06
    Names
    -0.06
    POSITIVE LOGITS
    ồm
    0.07
     duplication
    0.06
     inferior
    0.06
    posables
    0.06
    Picture
    0.06
    uerdo
    0.06
    Measure
    0.06
    olik
    0.06
    icip
    0.06
     Cuisine
    0.06
    Act Density 0.013%

    No Known Activations