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

    Neuronpedia

    INDEX
    Explanations

    ethical alternatives and uses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Uid
    0.47
    Ст
    0.46
     toget
    0.40
    ㄒ
    0.39
     freuen
    0.39
     weekly
    0.38
    Ը
    0.38
     Motto
    0.38
     Synonym
    0.38
    син
    0.38
    POSITIVE LOGITS
     eb
    0.43
    eb
    0.40
     EB
    0.37
    EB
    0.37
     substrates
    0.35
    shims
    0.34
     evaluates
    0.34
     Lear
    0.34
     considerable
    0.34
     substrate
    0.33
    Act Density 0.000%

    No Known Activations