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

    Neuronpedia

    INDEX
    Explanations

    tree data structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OS
    0.73
    Э
    0.58
     os
    0.55
     servizio
    0.55
    IS
    0.53
    UM
    0.52
    SE
    0.52
    ist
    0.51
    IST
    0.51
    ES
    0.50
    POSITIVE LOGITS
     treks
    0.60
     telenov
    0.56
    लाम
    0.55
     தவற
    0.53
    మయ్య
    0.50
    bab
    0.50
     videos
    0.49
     précédemment
    0.48
    ዎቹ
    0.47
    enten
    0.47
    Act Density 0.004%

    No Known Activations