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

    Neuronpedia

    INDEX
    Explanations

    formal definition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ri
    0.59
    je
    0.53
    kk
    0.52
    km
    0.52
    pm
    0.51
    us
    0.50
    odo
    0.49
    ree
    0.48
    ve
    0.48
    ha
    0.47
    POSITIVE LOGITS
     micró
    0.46
     équipements
    0.46
     ακόμη
    0.46
     niedrig
    0.46
     compléter
    0.44
     voorkomen
    0.44
     reconnaître
    0.43
    铸
    0.43
     guér
    0.43
     назем
    0.43
    Act Density 0.006%

    No Known Activations