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

    Neuronpedia

    INDEX
    Explanations

    what is the meaning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    abilecek
    0.55
     존재하는
    0.52
    ツー
    0.52
    Ⴊ
    0.51
     차량
    0.48
     프랑
    0.48
     Євро
    0.48
    𝒑
    0.48
    逅
    0.47
    ﮄ
    0.46
    POSITIVE LOGITS
     equivalents
    0.47
     integrated
    0.45
     aqu
    0.45
     locations
    0.45
     attackers
    0.44
     offerings
    0.44
     options
    0.44
     substitutions
    0.44
     placing
    0.44
     reputations
    0.44
    Act Density 0.000%

    No Known Activations