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

    Neuronpedia

    INDEX
    Explanations

    selected

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     minister
    -0.07
    ינוי
    -0.07
    ince
    -0.07
    ✾
    -0.07
    (no
    -0.06
     sư
    -0.06
     Meteor
    -0.06
    insk
    -0.06
     Slut
    -0.06
     cookie
    -0.06
    POSITIVE LOGITS
     carrots
    0.08
    ﮔ
    0.07
    惊喜
    0.07
    责任制
    0.07
    参与者
    0.07
     premium
    0.07
     wholesalers
    0.07
    .setOnItemClickListener
    0.07
    	pop
    0.07
    @AllArgsConstructor
    0.07
    Act Density 0.010%

    No Known Activations