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

    Neuronpedia

    INDEX
    Explanations

    counting or indexing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    getWorld
    0.73
    ủi
    0.69
    どり
    0.67
     그리고
    0.67
     Pick
    0.65
     Univer
    0.65
    Turn
    0.65
    ău
    0.65
    finally
    0.64
    Gang
    0.64
    POSITIVE LOGITS
     eins
    0.84
     pellets
    0.78
     অনুরাগ
    0.75
     pensa
    0.75
    𝚅
    0.73
     foothold
    0.72
     theseKeys
    0.72
     cita
    0.72
     bicara
    0.72
     Endo
    0.72
    Act Density 0.001%

    No Known Activations