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

    Neuronpedia

    INDEX
    Explanations

    being involved

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    LabelText
    -0.07
    AFP
    -0.07
    инок
    -0.07
    GRES
    -0.07
    	A
    -0.06
     Lear
    -0.06
    aru
    -0.06
     trackers
    -0.06
    AccessType
    -0.06
     Emil
    -0.06
    POSITIVE LOGITS
    ض
    0.07
     xuyên
    0.07
    Thought
    0.06
    }");↵
    0.06
     Grill
    0.06
    }`)↵
    0.06
    -heart
    0.06
    .Package
    0.06
     sırada
    0.06
    +</
    0.06
    Act Density 0.040%

    No Known Activations