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

    Neuronpedia

    INDEX
    Explanations

    hydrogen bonds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Venice
    0.45
     fatt
    0.41
     SUBJECT
    0.40
     palms
    0.39
     Theodore
    0.38
    :
    0.38
     es
    0.38
    lections
    0.38
     Browne
    0.38
    "
    0.38
    POSITIVE LOGITS
     estren
    0.50
    애
    0.48
    ತ್ವ
    0.48
    ଏ
    0.48
     एक्ट
    0.47
    nvim
    0.46
    ಶಾ
    0.46
    ρει
    0.46
     Adapt
    0.45
    할
    0.45
    Act Density 0.003%

    No Known Activations