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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    맏
    0.40
    lios
    0.38
    ያስ
    0.38
    하였
    0.38
    isements
    0.37
    žete
    0.37
    ড়ে
    0.36
    buildSpec
    0.36
    认为
    0.36
    Caprio
    0.36
    POSITIVE LOGITS
     দেখি
    0.42
     fibrous
    0.38
     MCS
    0.38
     fridge
    0.38
     fromi
    0.37
     tapi
    0.37
    Henry
    0.37
    Jackson
    0.37
    いくつか
    0.37
     bbs
    0.36
    Act Density 0.004%

    No Known Activations