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

    Neuronpedia

    INDEX
    Explanations

    initial stages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    喚
    0.42
    後に
    0.37
    唤
    0.37
    ließlich
    0.37
     आखिरकार
    0.36
    வையாக
    0.36
    ोजक
    0.36
    随后
    0.35
    ित्य
    0.35
     গম্ভীর
    0.35
    POSITIVE LOGITS
     initial
    1.21
     initially
    1.16
     Initially
    1.04
     Initial
    1.00
    前期
    0.98
     initiale
    0.98
    initial
    0.97
    初期
    0.97
    Initial
    0.96
     inital
    0.96
    Act Density 0.219%

    No Known Activations