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

    Neuronpedia

    INDEX
    Explanations

    we followed by action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Nói
    0.41
    noons
    0.38
    ρέπει
    0.37
    heets
    0.37
    harth
    0.37
     parla
    0.36
    పోయ
    0.36
     سيدنا
    0.36
    SNL
    0.36
    getInputStream
    0.36
    POSITIVE LOGITS
    finally
    0.43
     totally
    0.43
     finally
    0.40
     supposed
    0.40
     firstly
    0.39
    totally
    0.39
    regarded
    0.39
     ente
    0.38
     snatch
    0.38
    hide
    0.37
    Act Density 0.004%

    No Known Activations