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

    Neuronpedia

    INDEX
    Explanations

    Quantities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     FOOT
    -0.07
     ساله
    -0.07
     Respons
    -0.07
     Nobel
    -0.07
    reminder
    -0.07
     Everest
    -0.06
    디어
    -0.06
     Sailor
    -0.06
     Globals
    -0.06
     kvinner
    -0.06
    POSITIVE LOGITS
    сі
    0.06
    γα
    0.06
    tenant
    0.06
     slight
    0.05
    ریان
    0.05
     ab
    0.05
    (in
    0.05
     înt
    0.05
     Evaluation
    0.05
     −
    0.05
    Act Density 0.025%

    No Known Activations