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

    Neuronpedia

    INDEX
    Explanations

    divine source, moral character, image names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     सक्
    0.50
     mortgage
    0.49
     imediat
    0.48
     donation
    0.47
     charitable
    0.47
     immediatamente
    0.47
     localVarAccept
    0.45
     hou
    0.45
     ople
    0.45
     leva
    0.44
    POSITIVE LOGITS
    Frames
    0.53
    purple
    0.50
    meshes
    0.50
    FRAME
    0.47
    fox
    0.46
    Rad
    0.45
    Framework
    0.45
    Attributes
    0.45
    frame
    0.44
    たっぷり
    0.43
    Act Density 0.000%

    No Known Activations