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

    Neuronpedia

    INDEX
    Explanations

    relative pronouns or possessives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    is
    0.56
     footprint
    0.50
    on
    0.45
    in
    0.44
     footprints
    0.44
    ையை
    0.43
    X
    0.43
    <img>
    0.43
    =
    0.43
    ing
    0.42
    POSITIVE LOGITS
     whom
    0.55
     الذين
    0.55
     Whom
    0.50
     जिनकी
    0.47
     हत्याकांड
    0.47
     wszel
    0.46
    是谁
    0.46
     whose
    0.46
     كلهم
    0.44
     cuyos
    0.43
    Act Density 0.066%

    No Known Activations