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

    Neuronpedia

    INDEX
    Explanations

    breaking the fast

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    订阅
    0.41
    loci
    0.39
    Formal
    0.38
    Kle
    0.38
    和田
    0.38
     сте
    0.37
    ónicos
    0.37
    ]</
    0.37
     கர
    0.37
     Νο
    0.37
    POSITIVE LOGITS
     breaking
    0.77
    breaking
    0.69
     buka
    0.69
    ফতার
    0.68
    ftar
    0.68
     Breaking
    0.60
    ift
    0.59
    Breaking
    0.58
     Su
    0.54
     berb
    0.54
    Act Density 0.001%

    No Known Activations