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

    Neuronpedia

    INDEX
    Explanations

    mental health resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    joe
    0.64
     prophyl
    0.58
    vell
    0.58
     négl
    0.58
     végétation
    0.56
    层的
    0.56
     Tall
    0.55
    ğine
    0.55
     Ve
    0.55
     প্রশস্ত
    0.54
    POSITIVE LOGITS
    IDA
    0.73
     አማ
    0.72
     st
    0.70
    ibar
    0.67
     sh
    0.67
    ashions
    0.67
     Sham
    0.66
    Static
    0.66
     ಶ
    0.66
    êts
    0.63
    Act Density 0.055%

    No Known Activations