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

    Neuronpedia

    INDEX
    Explanations

    Here's a breakdown

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    not
    0.42
    NOT
    0.41
    ozen
    0.40
    ependant
    0.40
     CUR
    0.40
     VAS
    0.40
    only
    0.39
    yed
    0.39
     Plessis
    0.39
    ylon
    0.39
    POSITIVE LOGITS
     вообще
    0.76
     Вообще
    0.70
     überhaupt
    0.63
     indeed
    0.62
     frankly
    0.55
     übrigens
    0.54
     alike
    0.54
    一样
    0.53
     similarly
    0.51
     equivalently
    0.51
    Act Density 0.073%

    No Known Activations