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

    Neuronpedia

    INDEX
    Explanations

    disclaimers and notes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     a
    0.59
     an
    0.57
     the
    0.49
     impure
    0.49
     atoms
    0.49
    াদিগের
    0.46
     cylind
    0.46
     heterogeneous
    0.46
     ẞ
    0.46
     thermodynam
    0.46
    POSITIVE LOGITS
    ↵↵
    0.77
     Also
    0.75
    Also
    0.75
     Additionally
    0.72
     Также
    0.66
    Additionally
    0.66
     También
    0.65
    ​​​​
    0.64
     Ayrıca
    0.64
    Website
    0.64
    Act Density 0.009%

    No Known Activations