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

    Neuronpedia

    INDEX
    Explanations

    impact

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    er
    0.59
    ed
    0.56
     simulate
    0.54
    ul
    0.54
     e
    0.53
    е
    0.52
    ijima
    0.50
    onder
    0.50
     u
    0.49
    utter
    0.49
    POSITIVE LOGITS
    낍
    0.52
     яхшы
    0.50
     språk
    0.50
    کی
    0.49
    ⬝
    0.49
     organisasi
    0.48
     APIDC
    0.48
     thèse
    0.47
     삶
    0.47
     abstractions
    0.47
    Act Density 0.000%

    No Known Activations