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

    Neuronpedia

    INDEX
    Explanations

    read-only and read-write

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ussians
    0.42
    каче
    0.37
     фунда
    0.37
    緞
    0.37
    elolaan
    0.37
    ahuasca
    0.36
    ゴン
    0.36
     தண்ணீ
    0.36
    ajos
    0.35
     корпу
    0.35
    POSITIVE LOGITS
    readonly
    1.33
     readonly
    1.26
    ReadOnly
    1.23
     Read
    0.86
     writable
    0.83
     read
    0.82
     RW
    0.82
     WRITE
    0.81
     Write
    0.78
    write
    0.76
    Act Density 0.029%

    No Known Activations