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

    Neuronpedia

    INDEX
    Explanations

    chat arena, models, users

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sint
    0.51
     Sint
    0.43
     GPIO
    0.43
    Height
    0.42
     biofilm
    0.41
    };
    0.41
    HTree
    0.41
    䓶
    0.41
     PET
    0.40
     cercano
    0.40
    POSITIVE LOGITS
    ne
    0.50
    ushed
    0.48
    jn
    0.48
    relations
    0.46
     blushing
    0.46
    co
    0.45
    never
    0.45
     बंगाल
    0.45
    no
    0.45
    now
    0.45
    Act Density 0.002%

    No Known Activations