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

    Neuronpedia

    INDEX
    Explanations

    phone number digits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    })"
    0.45
    "})
    0.43
     ",")
    0.42
     "}
    0.41
    ")))
    0.40
    ")}
    0.39
    "}}
    0.39
     ""}
    0.39
     )}
    0.39
    "]}
    0.39
    POSITIVE LOGITS
    orns
    0.42
    <0xED>
    0.39
    स्ड
    0.38
    힙
    0.37
    사의
    0.37
    ATED
    0.36
     세계
    0.36
    ㅣ
    0.35
    ichever
    0.35
    ਾਕ
    0.35
    Act Density 0.005%

    No Known Activations