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

    Neuronpedia

    INDEX
    Explanations

    I'm / I statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    さり
    0.76
     Omnibus
    0.70
     మంది
    0.69
     ছিল
    0.65
     অধ্যক্ষ
    0.64
     यूनिवर्सल
    0.64
     られ
    0.64
    暨
    0.63
    raient
    0.63
     yester
    0.63
    POSITIVE LOGITS
     hope
    1.77
     apologize
    1.72
     promise
    1.46
     apologise
    1.44
     encourage
    1.41
     urge
    1.33
     invite
    1.31
    hope
    1.28
     recommend
    1.26
     apologies
    1.24
    Act Density 0.250%

    No Known Activations