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

    Neuronpedia

    INDEX
    Explanations

    make mistakes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Manning
    0.36
     manifesto
    0.36
     understood
    0.35
     maya
    0.35
     serial
    0.35
    ave
    0.34
    decorate
    0.34
    Landau
    0.34
    諳
    0.34
    Cue
    0.34
    POSITIVE LOGITS
     weld
    0.75
     Weld
    0.73
     Greeley
    0.67
     Lov
    0.64
    Lov
    0.60
     Berth
    0.59
     welding
    0.52
    焊接
    0.52
     lov
    0.51
     welded
    0.50
    Act Density 0.002%

    No Known Activations