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

    Neuronpedia

    INDEX
    Explanations

    transportation, arrival, and loading processes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rasgos
    1.74
    𝓽
    1.51
    हारी
    1.47
     році
    1.45
     году
    1.44
    sage
    1.42
    accia
    1.40
    𝐬
    1.40
     roommates
    1.38
    nabla
    1.38
    POSITIVE LOGITS
    न
    1.32
    alors
    1.30
    క
    1.26
    なぜ
    1.26
    вропей
    1.25
    യി
    1.24
    嶉
    1.21
    ণ
    1.19
    CONNECTION
    1.19
     systolic
    1.18
    Act Density 0.022%

    No Known Activations