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

    Neuronpedia

    INDEX
    Explanations

    academic citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     get
    0.78
     getting
    0.66
     backlog
    0.63
     payment
    0.61
     friends
    0.60
     project
    0.60
     free
    0.57
     det
    0.57
     feeling
    0.56
     parking
    0.56
    POSITIVE LOGITS
    cited
    1.28
     citado
    1.24
     cited
    1.21
    citing
    0.99
     citing
    0.98
     cites
    0.98
     énon
    0.97
    指出
    0.96
     cite
    0.95
    .).
    0.95
    Act Density 0.098%

    No Known Activations