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

    Neuronpedia

    INDEX
    Explanations

    specific items/details

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     disconnecting
    0.63
    eros
    0.60
    夷
    0.59
    ユニット
    0.57
     behold
    0.57
     installing
    0.56
     jar
    0.55
    Daw
    0.55
     Naz
    0.55
     substituting
    0.55
    POSITIVE LOGITS
     Cushion
    0.57
    urance
    0.57
     Add
    0.53
     প্রাণে
    0.53
     válida
    0.53
     bénéf
    0.52
    URANCE
    0.51
    っいて
    0.51
     ``
    0.51
     আভ
    0.51
    Act Density 0.001%

    No Known Activations