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

    Neuronpedia

    INDEX
    Explanations

    land, owns, variations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TableModel
    0.44
    restriction
    0.44
    dataframe
    0.43
    voegd
    0.42
    sbParams
    0.41
     அறிக்க
    0.40
     drm
    0.39
    ónicos
    0.38
     NOTICE
    0.38
    푀
    0.38
    POSITIVE LOGITS
     approves
    0.40
     approve
    0.38
     Georgia
    0.38
     minute
    0.38
     approved
    0.38
     Hide
    0.37
     luxuri
    0.37
    粤
    0.37
     hide
    0.36
     fractions
    0.36
    Act Density 0.000%

    No Known Activations