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

    Neuronpedia

    INDEX
    Explanations

    name

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    prising
    -0.07
     bowed
    -0.06
    ircle
    -0.06
     }}"
    -0.06
     obrov
    -0.06
     Flowers
    -0.06
     tob
    -0.06
    Hero
    -0.06
     freder
    -0.06
    -horizontal
    -0.06
    POSITIVE LOGITS
    ��
    0.07
     concess
    0.07
     estable
    0.06
     legisl
    0.06
    estli
    0.06
    typing
    0.06
    @example
    0.06
     ToDo
    0.06
     encouraged
    0.06
     workshop
    0.06
    Act Density 0.004%

    No Known Activations