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

    Neuronpedia

    INDEX
    Explanations

    phone number parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    except
    0.70
    och
    0.67
    ece
    0.66
    ください
    0.66
    ↵↵
    0.66
    ಟ್
    0.66
    head
    0.66
    e
    0.65
    use
    0.63
     except
    0.63
    POSITIVE LOGITS
     這
    0.83
    싫
    0.82
    בין
    0.81
    Если
    0.81
    ម្លៃ
    0.81
    ጒ
    0.79
     Sabemos
    0.79
     این
    0.78
     pierde
    0.78
    ﻛ
    0.78
    Act Density 0.118%

    No Known Activations