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

    Neuronpedia

    INDEX
    Explanations

    code identifiers and assignments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     annunci
    0.40
     sécrétion
    0.38
     altre
    0.37
     Ives
    0.36
     lapar
    0.35
    aroos
    0.35
    formations
    0.35
     wearables
    0.35
     biops
    0.35
     аппара
    0.34
    POSITIVE LOGITS
    Hello
    0.36
    Quick
    0.36
     القرار
    0.35
    Criteria
    0.34
    Into
    0.34
    Old
    0.34
    Voltage
    0.34
     nigh
    0.34
    Mode
    0.33
     والق
    0.33
    Act Density 0.003%

    No Known Activations