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

    Neuronpedia

    INDEX
    Explanations

    arguments and call to action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Gate
    0.70
    Gate
    0.69
     Node
    0.69
     airfoil
    0.68
     gate
    0.67
    ied
    0.66
     ne
    0.65
     языка
    0.65
     Ingl
    0.64
     Ireland
    0.63
    POSITIVE LOGITS
    tay
    0.63
     म्हणा
    0.58
    VV
    0.57
    urare
    0.57
    ()->
    0.56
    ยว
    0.55
    TAP
    0.55
    严
    0.54
    컨
    0.53
     Humanities
    0.52
    Act Density 0.134%

    No Known Activations