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

    Neuronpedia

    INDEX
    Explanations

    food descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ocrine
    0.41
     предлага
    0.39
    iel
    0.39
    ▩
    0.39
    损害
    0.38
    YLE
    0.37
    rte
    0.37
     уже
    0.37
    lle
    0.36
    iels
    0.36
    POSITIVE LOGITS
     Identify
    0.40
     identify
    0.39
     embarrass
    0.38
     formular
    0.37
    דו
    0.36
    owania
    0.35
     डीएस
    0.35
    owaniu
    0.35
    情形
    0.35
    identify
    0.35
    Act Density 0.000%

    No Known Activations