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

    Neuronpedia

    INDEX
    Explanations

    model providing data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    koliko
    0.39
     ملے
    0.37
    だけに
    0.36
    的力量
    0.36
    禧
    0.36
    jahteraan
    0.36
     মানুষদের
    0.36
     Dayan
    0.35
    的人
    0.35
     سکے۔
    0.35
    POSITIVE LOGITS
     terrain
    0.41
     equivariant
    0.40
     Universal
    0.40
    Terrain
    0.39
     Terrain
    0.38
     предназна
    0.38
    wijl
    0.37
     disregard
    0.37
    መሳሳይ
    0.37
     published
    0.36
    Act Density 0.004%

    No Known Activations